Triple
T3642961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Harbaugh |
E77231
|
entity |
| Predicate | styleOfPlayEmphasized |
P17512
|
FINISHED |
| Object | strong defense |
—
|
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: strong defense | Statement: [John Harbaugh, styleOfPlayEmphasized, strong defense]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: styleOfPlayEmphasized Context triple: [John Harbaugh, styleOfPlayEmphasized, strong defense]
-
A.
styleOfPlay
Indicates the characteristic manner or approach in which an entity performs or behaves, especially in a game, sport, or artistic context.
-
B.
usedInPlayByPlayFor
Indicates that something (such as data, terminology, or a resource) is utilized within the context of a play-by-play account or commentary.
-
C.
performanceStyle
Indicates the manner or style in which an action, work, or performance is carried out or presented.
-
D.
strategyEmphasis
chosen
Indicates an entity’s primary focus or priority within a broader strategy or plan.
-
E.
notablePlayType
Indicates that a particular type or category of play is especially significant or characteristic for the subject.
- 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_69ad85de1b988190a45f8dbfebc806fc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc35acf2c81908f60168e93b773b1 |
completed | March 8, 2026, 6:43 p.m. |
| PD | Predicate disambiguation | batch_69adb8445b2c8190ab07f6ad4e010d0e |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.