Triple
T23703383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TAS |
E585652
|
entity |
| Predicate | hasPanelOf |
P42161
|
FINISHED |
| Object | arbitrators specialized in sports law |
—
|
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: arbitrators specialized in sports law | Statement: [TAS, hasPanelOf, arbitrators specialized in sports law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPanelOf Context triple: [TAS, hasPanelOf, arbitrators specialized in sports law]
-
A.
hasPanel
chosen
Indicates that one entity includes, is equipped with, or is associated with a panel as a component or feature.
-
B.
hasPanelComposition
Indicates that something is composed of or structured into multiple panels or panel-like sections.
-
C.
hasInformationPanels
Indicates that an entity is equipped with or accompanied by informational panels that provide explanatory or descriptive content.
-
D.
hasSculptedPanels
Indicates that an entity features or includes panels that have been sculpted as part of its design or structure.
-
E.
panels
Indicates that one entity is composed of, covered by, or divided into flat sections or segments formed by another entity.
- 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_69e24904bd508190abfcb74855de2918 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b684e0a88190b7edeb102585ae9d |
completed | April 29, 2026, 7:43 a.m. |
| PD | Predicate disambiguation | batch_69f155d5265881908e43a9696b6a6d0f |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 6:53 p.m.