Triple
T20170496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hezhe |
E491944
|
entity |
| Predicate | relatedEthnicGroup |
P1969
|
FINISHED |
| Object | Oroqen |
—
|
NE NERFINISHED |
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: Oroqen | Statement: [Hezhe, relatedEthnicGroup, Oroqen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oroqen Context triple: [Hezhe, relatedEthnicGroup, Oroqen]
-
A.
Oroqen
chosen
The Oroqen are a small Tungusic-speaking indigenous people of northeastern China, traditionally known as hunters and reindeer herders living in the forests of the Greater and Lesser Khingan Mountains.
-
B.
Orokam
Orokam is a dialect of the Idoma language spoken by a subgroup of the Idoma people in central Nigeria.
-
C.
Orahili
Orahili is a traditional village on Indonesia’s Nias Island known for its distinctive vernacular architecture and preserved local customs.
-
D.
Otuoke
Otuoke is a town in Bayelsa State, Nigeria, known as the hometown of former President Goodluck Jonathan.
-
E.
Aroroy
Aroroy is a coastal municipality in the province of Masbate in the Philippines, known historically for its gold mining and fishing industries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66847ed9481908e6b23b399fa7005 |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:35 p.m.