Triple
T30914548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Denzel Ward |
E787541
|
entity |
| Predicate | playsDefensiveBackfieldPosition |
P87906
|
FINISHED |
| Object | cornerback |
—
|
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: cornerback | Statement: [Denzel Ward, playsDefensiveBackfieldPosition, cornerback]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playsDefensiveBackfieldPosition Context triple: [Denzel Ward, playsDefensiveBackfieldPosition, cornerback]
-
A.
defensivePositionHeldBy
chosen
Indicates that a specific defensive position or role is occupied or maintained by a particular entity.
-
B.
defensiveRole
Indicates that an entity serves a protective or guarding function in relation to another entity or context.
-
C.
primaryDefensiveLine
Indicates the main line of defense that first engages or protects against an opposing force or threat.
-
D.
defensiveTackle
Indicates that an entity plays the defensive tackle position, typically lining up on the interior of the defensive line to disrupt offensive plays.
-
E.
defensiveSide
Indicates which entity is acting in a defensive role or position relative to another entity or situation.
- 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_69f224be300c8190a6513ce1ee0a7026 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 29, 2026, 8:51 p.m.