Triple
T17435191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troy Kotsur |
E423983
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | American Sign Language |
—
|
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: American Sign Language | Statement: [Troy Kotsur, language, American Sign Language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: American Sign Language Context triple: [Troy Kotsur, language, American Sign Language]
-
A.
American Sign Language
chosen
American Sign Language is a natural visual-gestural language used primarily by Deaf communities in the United States and parts of Canada, with its own distinct grammar and vocabulary separate from spoken English.
-
B.
ASL
ASL is the ICAO airline designator used to identify Air Serbia in international aviation operations and communications.
-
C.
ASL
ASL is the three-letter station code used to identify Arsenal Underground station on the London Underground network.
-
D.
ASL
ASL is an international scholarly organization devoted to the advancement of research and education in symbolic logic and its applications.
-
E.
ASL
ASL is a German vehicle registration code used for cars registered in the Salzlandkreis district of Saxony-Anhalt.
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4490361c081908fd24f9a812f212c |
completed | April 19, 2026, 3:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.