Triple

T9577715
Position Surface form Disambiguated ID Type / Status
Subject Sawunese language E231085 entity
Predicate glottologName P6521 FINISHED
Object Sawu
Sawu is an Austronesian language spoken primarily on Savu (Sawu) Island in eastern Indonesia.
E809251 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: Sawu | Statement: [Sawunese language, glottologName, Sawu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sawu
Context triple: [Sawunese language, glottologName, Sawu]
  • A. Watampone
    Watampone is the main urban and administrative center of Bone Regency in South Sulawesi, Indonesia.
  • B. Kali Mata
    Kali Mata is a fierce and widely revered Hindu goddess, regarded as a powerful form of the Divine Mother associated with time, destruction of evil, and spiritual liberation.
  • C. Mendanau
    Mendanau is an island in Indonesia’s Bangka Belitung province, known for its coastal landscapes and role in the region’s maritime and fishing activities.
  • D. Sukoró
    Sukoró is a village in Hungary’s Fejér County, known as a lakeside resort and recreational area on the northern shore of Lake Velence.
  • E. Waingapu
    Waingapu is the main urban and economic center of the Indonesian island of Sumba, serving as a key hub for transportation and regional administration.
  • 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: Sawu
Triple: [Sawunese language, glottologName, Sawu]
Generated description
Sawu is an Austronesian language spoken primarily on Savu (Sawu) Island in eastern Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sawu
Target entity description: Sawu is an Austronesian language spoken primarily on Savu (Sawu) Island in eastern Indonesia.
  • A. Watampone
    Watampone is the main urban and administrative center of Bone Regency in South Sulawesi, Indonesia.
  • B. Kali Mata
    Kali Mata is a fierce and widely revered Hindu goddess, regarded as a powerful form of the Divine Mother associated with time, destruction of evil, and spiritual liberation.
  • C. Mendanau
    Mendanau is an island in Indonesia’s Bangka Belitung province, known for its coastal landscapes and role in the region’s maritime and fishing activities.
  • D. Sukoró
    Sukoró is a village in Hungary’s Fejér County, known as a lakeside resort and recreational area on the northern shore of Lake Velence.
  • E. Waingapu
    Waingapu is the main urban and economic center of the Indonesian island of Sumba, serving as a key hub for transportation and regional administration.
  • 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_69ca848091c48190bc313d6620d09555 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd99ad7d108190a0b8c975351ea727 completed April 1, 2026, 10:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69d16155b3288190ac135c3a1e58cc7e completed April 4, 2026, 7:07 p.m.
NEDg Description generation batch_69d161e6a1308190932c8386e1c24f2e completed April 4, 2026, 7:09 p.m.
NED2 Entity disambiguation (via description) batch_69d165a8c80081909e4d0837cbaabf95 completed April 4, 2026, 7:25 p.m.
Created at: March 30, 2026, 8:05 p.m.