Triple
T23221792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lai people |
E580913
|
entity |
| Predicate | hasSubgroup |
P747
|
FINISHED |
| Object | Hakha Lai |
—
|
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: Hakha Lai | Statement: [Lai people, hasSubgroup, Hakha Lai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hakha Lai Context triple: [Lai people, hasSubgroup, Hakha Lai]
-
A.
Hakha Chin
chosen
Hakha Chin is a Tibeto-Burman language spoken primarily by the Chin people in and around the town of Hakha in Chin State, Myanmar.
-
B.
Hakha
Hakha is a hill town in western Myanmar that serves as the administrative and cultural center of the Chin people.
-
C.
Khoksa
Khoksa is a town and administrative unit in western Bangladesh, situated within the Kushtia District of the Khulna Division.
-
D.
Harlakhi
Harlakhi is a town in the Madhubani district of Bihar, India, known for its proximity to the India–Nepal border and its association with the Mithila region.
-
E.
Khakhaure
Khakhaure is the throne name (praenomen) of the ancient Egyptian pharaoh Menkaura, a ruler of the Old Kingdom’s Fourth Dynasty best known for his pyramid at Giza.
- 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1922924308190a26b00e09ce60ecd |
completed | April 29, 2026, 5:07 a.m. |
Created at: April 17, 2026, 4:08 p.m.