Triple
T1578771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bobby Hull |
E33713
|
entity |
| Predicate | WHAContract |
P32826
|
FINISHED |
| Object | first $1 million contract in professional hockey |
—
|
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: first $1 million contract in professional hockey | Statement: [Bobby Hull, WHAContract, first $1 million contract in professional hockey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: WHAContract Context triple: [Bobby Hull, WHAContract, first $1 million contract in professional hockey]
-
A.
WHA_draftYear
Indicates the year in which an entity was selected or entered into a professional draft.
-
B.
WHA_draftedBy
Indicates that a written work, document, or text was created or composed by a specific author or drafting entity.
-
C.
playedInWHASeasons
Indicates that an entity (typically a player) participated in one or more seasons of the World Hockey Association (WHA).
-
D.
WHA_draftOverall
Indicates the overall draft status or outcome associated with an entity, summarizing its current stage or result in a drafting process.
-
E.
WHA_draftRound
Indicates the specific round in which an entity was selected during a draft process.
- 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_69a885f27a4c8190a4622252cdf54c00 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abacfb1144819080c5687175aba1e1 |
completed | March 7, 2026, 4:43 a.m. |
| PD | Predicate disambiguation | batch_69aa61b0f5bc8190b1dc272990a59c13 |
completed | March 6, 2026, 5:10 a.m. |
| PDg | Predicate description generation | batch_69abacf991148190b20521c063f93bfd |
completed | March 7, 2026, 4:43 a.m. |
Created at: March 4, 2026, 7:27 p.m.