Triple
T2122240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tregami language |
E43949
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Tregami Kati |
E228160
|
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: Tregami Kati | Statement: [Tregami language, hasAlternativeName, Tregami Kati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tregami Kati Context triple: [Tregami language, hasAlternativeName, Tregami Kati]
-
A.
Tregami
chosen
Tregami is a Nuristani language spoken by a small community in eastern Afghanistan’s remote valleys.
-
B.
Trique
Trique is an indigenous Mesoamerican language spoken in Oaxaca, Mexico, known for its complex tonal system and belonging to the Oto-Manguean language family.
-
C.
Trife
Trife is a rapper best known as a member of the Brooklyn hip hop collective Junior M.A.F.I.A.
-
D.
Atripé
Atripé was an ancient Egyptian town in Upper Egypt notable as the home of the influential Coptic monastic leader Shenoute.
-
E.
TriG
TriG is a serialization format for RDF that extends Turtle to support the representation of named graphs and datasets.
- 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_69a88717cfe48190b7ecdd68c824848a |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbb51e8088190a1aeafee4e8dff63 |
completed | March 7, 2026, 5:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae58cd22c8819096dfd06d16703bf8 |
completed | March 9, 2026, 5:21 a.m. |
Created at: March 4, 2026, 7:44 p.m.