Triple
T30714283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duane Bobick |
E781978
|
entity |
| Predicate | careerSetback |
P117819
|
FINISHED |
| Object | knockout loss in a major televised bout |
—
|
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: knockout loss in a major televised bout | Statement: [Duane Bobick, careerSetback, knockout loss in a major televised bout]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: careerSetback Context triple: [Duane Bobick, careerSetback, knockout loss in a major televised bout]
-
A.
sufferedSetback
chosen
Indicates that an entity has experienced a negative event or obstacle that hindered its progress or success.
-
B.
careerImpact
Indicates how one entity influences or changes another entity’s professional trajectory, opportunities, or outcomes.
-
C.
experienceDropped
Indicates that an entity’s level of experience has decreased compared to a previous state or reference point.
-
D.
careerTackles
Indicates the total number of tackles a player has made over the course of their entire career.
-
E.
interruptedCareerBy
Indicates that an entity’s career was halted, delayed, or disrupted by another specified event or circumstance.
- 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_69f224acd24481908ed5f96f0d69b5dd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68c20d09481908f566241722507d3 |
completed | May 2, 2026, 11:43 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:35 p.m.