Triple
T2231010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PIT |
E48763
|
entity |
| Predicate | leagueAbbreviationStandard |
P3776
|
FINISHED |
| Object | NHL team code |
—
|
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: NHL team code | Statement: [PIT, leagueAbbreviationStandard, NHL team code]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leagueAbbreviationStandard Context triple: [PIT, leagueAbbreviationStandard, NHL team code]
-
A.
leagueAbbreviation
Indicates that an entity is identified by a shortened or abbreviated form of its league name.
-
B.
leagueAssociations
Indicates a relationship where an entity is formally connected to, participates in, or is governed by a particular league or set of leagues.
-
C.
abbreviationOfTeam
chosen
Indicates that one term is an abbreviation or shortened form of a team’s full name.
-
D.
stateLeague
Indicates that a sports team or club competes in, or is affiliated with, a particular state-level league or competition.
-
E.
NBAteam
Indicates that one entity is a professional basketball team that competes in the National Basketball Association (NBA) and the other entity is associated with it in that team role.
- 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_69a88aa51b388190949868ec9766e587 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc06b7374819089fe643e12797bfd |
completed | March 7, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69abbdadbb0c8190b3a1ede31b8acbfa |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.