Triple

T9577653
Position Surface form Disambiguated ID Type / Status
Subject Rote languages E231084 entity
Predicate hasPart P35 FINISHED
Object Keka language
Keka is an Austronesian language spoken on Rote Island in Indonesia, belonging to the Rote subgroup of languages.
 E809248 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: Keka language | Statement: [Rote languages, hasPart, Keka language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Keka language
Context triple: [Rote languages, hasPart, Keka language]
  • A. Kaera language
    The Kaera language is a Papuan language spoken by a small community on Pantar Island in eastern Indonesia.
  • B. Daakaka language
    The Daakaka language is an Oceanic language spoken by communities on Ambrym Island in Vanuatu.
  • C. Kreda language
    The Kreda language is an Eastern Saharan language spoken by the Kreda (Karai) people, primarily in parts of Chad and neighboring regions.
  • D. Khezha language
    The Khezha language is a Sino-Tibetan language spoken primarily by the Chakhesang Naga community in northeastern India.
  • E. Jakaltek language
    The Jakaltek language is a Mayan language spoken primarily by the Jakaltek (Popti’) people of northwestern Guatemala and parts of southern Mexico.
  • 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: Keka language
Triple: [Rote languages, hasPart, Keka language]
Generated description
Keka is an Austronesian language spoken on Rote Island in Indonesia, belonging to the Rote subgroup of languages.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Keka language
Target entity description: Keka is an Austronesian language spoken on Rote Island in Indonesia, belonging to the Rote subgroup of languages.
  • A. Kaera language
    The Kaera language is a Papuan language spoken by a small community on Pantar Island in eastern Indonesia.
  • B. Daakaka language
    The Daakaka language is an Oceanic language spoken by communities on Ambrym Island in Vanuatu.
  • C. Kreda language
    The Kreda language is an Eastern Saharan language spoken by the Kreda (Karai) people, primarily in parts of Chad and neighboring regions.
  • D. Khezha language
    The Khezha language is a Sino-Tibetan language spoken primarily by the Chakhesang Naga community in northeastern India.
  • E. Jakaltek language
    The Jakaltek language is a Mayan language spoken primarily by the Jakaltek (Popti’) people of northwestern Guatemala and parts of southern Mexico.
  • 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.