Triple

T1532920
Position Surface form Disambiguated ID Type / Status
Subject Flores–Lembata languages E32484 entity
Predicate hasMember P10 FINISHED
Object Keo language
The Keo language is an Austronesian language spoken by the Keo people on Flores Island in Indonesia.
 E174816 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: Keo language | Statement: [Flores–Lembata languages, hasMember, Keo language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Keo language
Context triple: [Flores–Lembata languages, hasMember, Keo language]
  • A. Koya language
    Koya language is a South-Central Dravidian language spoken by the Koya tribal communities in central and southern India.
  • B. Kove language
    The Kove language is an Austronesian language spoken by the Kove people of New Britain in Papua New Guinea.
  • C. Kokota language
    The Kokota language is an Austronesian language spoken by the Kokota people of Santa Isabel Island in the Solomon Islands.
  • D. Lemolang language
    Lemolang is an Austronesian language spoken by a small community in South Sulawesi, Indonesia.
  • E. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • 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: Keo language
Triple: [Flores–Lembata languages, hasMember, Keo language]
Generated description
The Keo language is an Austronesian language spoken by the Keo people on Flores Island in Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Keo language
Target entity description: The Keo language is an Austronesian language spoken by the Keo people on Flores Island in Indonesia.
  • A. Koya language
    Koya language is a South-Central Dravidian language spoken by the Koya tribal communities in central and southern India.
  • B. Kove language
    The Kove language is an Austronesian language spoken by the Kove people of New Britain in Papua New Guinea.
  • C. Kokota language
    The Kokota language is an Austronesian language spoken by the Kokota people of Santa Isabel Island in the Solomon Islands.
  • D. Lemolang language
    Lemolang is an Austronesian language spoken by a small community in South Sulawesi, Indonesia.
  • E. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • 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_69a885ea86308190998f6bc14bb91f8e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9081835e4819093dee004fdb027ff completed March 5, 2026, 4:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad295a03d881909071fb437c2d19ba completed March 8, 2026, 7:46 a.m.
NEDg Description generation batch_69ad2a1957e481908b07d3f4df75fbfe completed March 8, 2026, 7:49 a.m.
NED2 Entity disambiguation (via description) batch_69ad2b2929348190ac35ff8d405894d6 completed March 8, 2026, 7:54 a.m.
Created at: March 4, 2026, 7:26 p.m.