Triple
T9085169
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haya people |
E217733
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Haya language |
E695726
|
NE FINISHED |
How this triple was built (2 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: Haya language | Statement: [Haya people, language, Haya language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haya language Context triple: [Haya people, language, Haya language]
-
A.
Haya language
chosen
Haya language is a Bantu language spoken primarily by the Haya people in northwestern Tanzania near Lake Victoria.
-
B.
Hayu language
The Hayu language is a lesser-known Sino-Tibetan language spoken by the Hayu ethnic group in eastern Nepal.
-
C.
Hani language
The Hani language is a Tibeto-Burman language spoken primarily by the Hani people in southwestern China and neighboring regions of Southeast Asia.
-
D.
Hixkaryana language
Hixkaryana is an indigenous Cariban language of northern Brazil, noted for its rare object–verb–subject (OVS) basic word order.
-
E.
Hewa language
The Hewa language is a lesser-known Austronesian language spoken on the Indonesian islands of Flores and/or Lembata, belonging to the Flores–Lembata subgroup.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca83d7a0388190ba1af89ed7ba36f9 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc960d0b008190b0e9e61fac45101d |
completed | April 1, 2026, 3:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cffe38f0048190a9fb15e73d9bcd50 |
completed | April 3, 2026, 5:51 p.m. |
Created at: March 30, 2026, 7:13 p.m.