Triple

T14824013
Position Surface form Disambiguated ID Type / Status
Subject Lake Turano E348524 entity
Predicate shoreHasSettlement P969 FINISHED
Object Antuni
Antuni is a small historic village in central Italy overlooking Lake Turano, known for its medieval architecture and scenic mountain-lake setting.
 E1122943 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: Antuni | Statement: [Lake Turano, shoreHasSettlement, Antuni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Antuni
Context triple: [Lake Turano, shoreHasSettlement, Antuni]
  • A. Anezal
    Anezal is a village located in the Jbel Sirwa mountain region of southern Morocco.
  • B. Atoni
    Atoni are an indigenous ethnic group of western Timor known for their traditional hierarchical social structure, distinctive architecture, and dryland farming culture.
  • C. Antrìm
    Antrìm is the Scots name for the town of Antrim in County Antrim, Northern Ireland.
  • D. Angoche
    Angoche is a coastal city in northern Mozambique known historically as an important Swahili trading port on the Indian Ocean.
  • E. Barasa
    Barasa is a tribal group indigenous to eastern Libya, traditionally associated with the region’s Bedouin Arab communities and local social structure.
  • 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: Antuni
Triple: [Lake Turano, shoreHasSettlement, Antuni]
Generated description
Antuni is a small historic village in central Italy overlooking Lake Turano, known for its medieval architecture and scenic mountain-lake setting.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Antuni
Target entity description: Antuni is a small historic village in central Italy overlooking Lake Turano, known for its medieval architecture and scenic mountain-lake setting.
  • A. Anezal
    Anezal is a village located in the Jbel Sirwa mountain region of southern Morocco.
  • B. Atoni
    Atoni are an indigenous ethnic group of western Timor known for their traditional hierarchical social structure, distinctive architecture, and dryland farming culture.
  • C. Antrìm
    Antrìm is the Scots name for the town of Antrim in County Antrim, Northern Ireland.
  • D. Angoche
    Angoche is a coastal city in northern Mozambique known historically as an important Swahili trading port on the Indian Ocean.
  • E. Barasa
    Barasa is a tribal group indigenous to eastern Libya, traditionally associated with the region’s Bedouin Arab communities and local social structure.
  • 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe7a8dc8190bcb5ecfa1cbf1601 completed April 14, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe389d7c848190813be06bed7813d7 completed May 8, 2026, 7:25 p.m.
NEDg Description generation batch_69fe5bc7e6848190a243bcfccaea3a37 completed May 8, 2026, 9:55 p.m.
NED2 Entity disambiguation (via description) batch_69fe5c271c6c8190bb4127cdf8af6647 completed May 8, 2026, 9:56 p.m.
Created at: April 10, 2026, 1:51 a.m.