Triple
T37758378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBA |
E941183
|
entity |
| Predicate | predecessorCommissioner |
P34201
|
FINISHED |
| Object | David Stern |
—
|
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: David Stern | Statement: [NBA, predecessorCommissioner, David Stern]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorCommissioner Context triple: [NBA, predecessorCommissioner, David Stern]
-
A.
originalCommissionerOf
Indicates that one entity is the person or organization that initially commissioned, ordered, or requested the creation or execution of another entity (such as a work, project, or service).
-
B.
predecessorCEO
Indicates that one person previously held the position of CEO before another specific person.
-
C.
predecessorInOffice
chosen
Indicates that one officeholder directly held a particular position before another officeholder in an official succession.
-
D.
predecessorName
Indicates that the value is the name of an entity that directly precedes another in an ordered sequence or lineage.
-
E.
formerDirector
Indicates that one entity previously held the position of director of the other entity but no longer does.
- F. None of above.
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_69f76ee1f3a88190834e6c8af99bccc9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe6e492bf8819080b25221d13445ea |
completed | May 8, 2026, 11:14 p.m. |
| PD | Predicate disambiguation | batch_69fe6dd33a6881908fe9bbbc184cab51 |
completed | May 8, 2026, 11:12 p.m. |
Created at: May 3, 2026, 4:19 p.m.