Triple
T15941021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Oleynick |
E386559
|
entity |
| Predicate | playedIn |
P2170
|
FINISHED |
| Object | NBA |
E941183
|
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: NBA | Statement: [Frank Oleynick, playedIn, NBA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NBA Context triple: [Frank Oleynick, playedIn, NBA]
-
A.
NBA
NBA is the vehicle registration code assigned to the town of Górowo Iławeckie in northern Poland.
-
B.
NBA
NBA is a vehicle registration code used in Poland, specifically associated with the town of Sępopol and its surrounding area.
-
C.
NBA
The NBA here refers to the Niger Basin Authority, an intergovernmental organization that coordinates regional cooperation and sustainable development among countries sharing the Niger River basin in West Africa.
-
D.
NBA
The National Board of Accreditation (NBA) is an autonomous body in India responsible for evaluating and accrediting technical and professional education programs to ensure quality and standards.
-
E.
NBA
chosen
The NBA (National Basketball Association) is the premier professional basketball league in North America, featuring the world's top male basketball players and teams.
- 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_69d86da750008190987eb26be3f6c118 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156cd3a188190a1a7dcbfdd38284c |
completed | April 16, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb5bbc07c819098fd768e2e6b5b3e |
completed | May 9, 2026, 10:31 p.m. |
Created at: April 10, 2026, 4:53 a.m.