Triple
T1413026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBA referees |
E31845
|
entity |
| Predicate | mustParticipateIn |
P4470
|
FINISHED |
| Object | video review sessions |
—
|
LITERAL 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: video review sessions | Statement: [NBA referees, mustParticipateIn, video review sessions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mustParticipateIn Context triple: [NBA referees, mustParticipateIn, video review sessions]
-
A.
regulatesParticipationIn
Indicates that one entity controls, directs, or sets rules governing another entity’s involvement in an activity, process, or system.
-
B.
participation
chosen
Indicates that an entity takes part in, contributes to, or is involved in a shared activity, event, or process with others.
-
C.
invitesParticipationOf
Indicates that one entity actively requests or encourages another entity to take part in an activity, event, or process.
-
D.
participationModel
Indicates how entities are involved in or contribute to an activity, process, or interaction.
-
E.
hasGlobalParticipation
Indicates that an entity is involved in or contributes to activities, initiatives, or operations that span multiple countries or have worldwide scope.
- 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_69a49919a994819086528951bc224775 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c3e476f08190aed1576805c62462 |
completed | March 1, 2026, 10:55 p.m. |
| PD | Predicate disambiguation | batch_69a4bf048b648190ab77d9b45cb4855f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.