Triple
T9031998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kuki |
E216393
|
entity |
| Predicate | linguisticVariety |
P41081
|
FINISHED |
| Object | Kom |
E593174
|
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: Kom | Statement: [Kuki, linguisticVariety, Kom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kom Context triple: [Kuki, linguisticVariety, Kom]
-
A.
Kom
chosen
Kom is an ethnic group and kingdom in northwestern Cameroon known for its rich cultural traditions, language, and chieftaincy system.
-
B.
Kon
Kon is a deity from Andean mythology often associated with rain, wind, and the fertilizing forces that sustain life in the region.
-
C.
Kar
Kar is the young, streetwise pickpocket chosen as the reluctant successor to a mystical protector in the action film "Bulletproof Monk."
-
D.
Konz
Konz is a town in western Germany near Trier, known for its location where the Saar River meets the Moselle.
-
E.
Ke
Ke is the given name of Ke Huy Quan, the Vietnamese-American actor and former child star known for roles in films like "Indiana Jones and the Temple of Doom," "The Goonies," and "Everything Everywhere All at Once."
- 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_69ca83d10b608190b2b2f8e0a7faaf14 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6a9f2c7481909b4a272183f20585 |
completed | April 1, 2026, 12:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdbc9c6e08190aa71d84316afc6d5 |
completed | April 3, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:08 p.m.