Triple
T23862237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TOR (AHL) |
E592479
|
entity |
| Predicate | primaryNHLMarket |
P54054
|
FINISHED |
| Object | Toronto |
—
|
NE NERFINISHED |
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: Toronto | Statement: [TOR (AHL), primaryNHLMarket, Toronto]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryNHLMarket Context triple: [TOR (AHL), primaryNHLMarket, Toronto]
-
A.
basedInLeagueMarket
Indicates that an entity’s primary market or operational base is located within the geographic market area associated with a particular league.
-
B.
hasFanBasePrimarilyIn
chosen
Indicates that an entity’s main or largest group of supporters, followers, or fans is located in a specified place or region.
-
C.
primaryHomeGroundNot
Indicates that the specified location is explicitly not the entity’s primary home ground.
-
D.
homeRegionLeague
Indicates that a league is the primary or native regional competition associated with an entity (such as a team or club).
-
E.
dominantMediaMarket
Indicates that one media market holds primary influence or control over another media market in terms of audience reach or content distribution.
- 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_69e25d22eb488190914b193aff952e83 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1cae0b4bc819089f491d9e817d160 |
completed | April 29, 2026, 9:09 a.m. |
| PD | Predicate disambiguation | batch_69f1614a65a88190bde1efb368a151e4 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:13 p.m.