Triple

T6564827
Position Surface form Disambiguated ID Type / Status
Subject Mwerlap E153876 entity
Predicate spokenIn P2266 FINISHED
Object Torres–Banks languages area
The Torres–Banks languages area is a region in northern Vanuatu known for its dense cluster of closely related Oceanic languages and rich linguistic diversity.
 E603828 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Torres–Banks languages area | Statement: [Mwerlap, spokenIn, Torres–Banks languages area]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Torres–Banks languages area
Context triple: [Mwerlap, spokenIn, Torres–Banks languages area]
  • A. Plateau linguistic area
    The Plateau linguistic area is a region of the North American Plateau where diverse Indigenous languages, often from different families, share common structural features due to long-term contact and interaction.
  • B. Sulawesi linguistic area
    The Sulawesi linguistic area is a region of the Indonesian island of Sulawesi characterized by intense contact among diverse Austronesian and Papuan languages, leading to shared structural features across otherwise unrelated language groups.
  • C. Philippine linguistic area
    The Philippine linguistic area is a region encompassing the Philippines where diverse Austronesian languages share common structural features due to long-term contact and convergence.
  • D. Plains linguistic area
    The Plains linguistic area is a region of North America where diverse Indigenous languages, including the Caddoan family, have converged and shared structural features through long-term contact.
  • E. Mesoamerican linguistic area
    The Mesoamerican linguistic area is a Sprachbund in which numerous indigenous language families, including Mayan, share convergent structural features due to long-term contact rather than common ancestry.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Torres–Banks languages area
Triple: [Mwerlap, spokenIn, Torres–Banks languages area]
Generated description
The Torres–Banks languages area is a region in northern Vanuatu known for its dense cluster of closely related Oceanic languages and rich linguistic diversity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Torres–Banks languages area
Target entity description: The Torres–Banks languages area is a region in northern Vanuatu known for its dense cluster of closely related Oceanic languages and rich linguistic diversity.
  • A. Plateau linguistic area
    The Plateau linguistic area is a region of the North American Plateau where diverse Indigenous languages, often from different families, share common structural features due to long-term contact and interaction.
  • B. Sulawesi linguistic area
    The Sulawesi linguistic area is a region of the Indonesian island of Sulawesi characterized by intense contact among diverse Austronesian and Papuan languages, leading to shared structural features across otherwise unrelated language groups.
  • C. Philippine linguistic area
    The Philippine linguistic area is a region encompassing the Philippines where diverse Austronesian languages share common structural features due to long-term contact and convergence.
  • D. Plains linguistic area
    The Plains linguistic area is a region of North America where diverse Indigenous languages, including the Caddoan family, have converged and shared structural features through long-term contact.
  • E. Mesoamerican linguistic area
    The Mesoamerican linguistic area is a Sprachbund in which numerous indigenous language families, including Mayan, share convergent structural features due to long-term contact rather than common ancestry.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c6880cb35881909b763eb0125236b9 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ae3b9ec8819080f3052556d95810 completed March 27, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d5622e0481909b0ac0f4e06d19bc completed March 27, 2026, 7:07 p.m.
NEDg Description generation batch_69c6d828620081909c1b4dfaa96efd62 completed March 27, 2026, 7:19 p.m.
NED2 Entity disambiguation (via description) batch_69c6d8a3d194819080f33e179a8a8679 completed March 27, 2026, 7:21 p.m.
Created at: March 27, 2026, 1:52 p.m.