Triple
T10994479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Hockey League |
E259826
|
entity |
| Predicate | hasRuleBookBasedOn |
P6249
|
FINISHED |
| Object | USA Hockey rules |
—
|
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: USA Hockey rules | Statement: [United States Hockey League, hasRuleBookBasedOn, USA Hockey rules]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRuleBookBasedOn Context triple: [United States Hockey League, hasRuleBookBasedOn, USA Hockey rules]
-
A.
hasRulebook
Indicates that one entity possesses, is governed by, or is associated with a specific rulebook.
-
B.
hasRule
Indicates that an entity is governed, constrained, or defined by a specific rule or set of rules.
-
C.
hasRuleOver
Indicates that one entity holds authority, control, or governance over another entity.
-
D.
isRuleGoverned
Indicates that an entity’s behavior, structure, or operation is determined and constrained by explicit rules or formal regulations.
-
E.
usesRulesFrom
chosen
Indicates that one entity applies, follows, or is governed by the rules defined or provided 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d795d460d88190bff918d6dfdb0f93 |
completed | April 9, 2026, 12:04 p.m. |
| PD | Predicate disambiguation | batch_69d72e93ac648190b46c5d12bf3eb1e9 |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:24 p.m.