Triple
T162109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conference USA |
E3309
|
entity |
| Predicate | hasRulebook |
P6248
|
FINISHED |
| Object | Conference USA bylaws |
—
|
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: Conference USA bylaws | Statement: [Conference USA, hasRulebook, Conference USA bylaws]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRulebook Context triple: [Conference USA, hasRulebook, Conference USA bylaws]
-
A.
hasRule
Indicates that an entity is governed, constrained, or defined by a specific rule or set of rules.
-
B.
notableRule
Indicates that a rule or regulation is particularly significant, prominent, or noteworthy within a given context.
-
C.
hasDesignatedPlayerRule
Indicates that a sports league or competition uses a designated player rule allowing certain players to be treated differently for roster or salary purposes.
-
D.
hasCheckAndBalanceWith
Indicates that two entities mutually monitor, limit, or counterbalance each other's powers or actions to prevent dominance or abuse.
-
E.
hasLiturgicalBook
Indicates that one entity possesses, uses, or is associated with a specific liturgical book in a religious or worship context.
- F. None of above. chosen
Provenance (4 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a2585877648190a2ec320182a69343 |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a256623704819089d9eeefe05858ce |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a2578329d08190be82e004b8224d2b |
completed | Feb. 28, 2026, 2:48 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.