Triple
T7236900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deshaun Watson |
E155251
|
entity |
| Predicate | positionStyle |
P75947
|
FINISHED |
| Object | dual-threat quarterback |
—
|
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: dual-threat quarterback | Statement: [Deshaun Watson, positionStyle, dual-threat quarterback]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionStyle Context triple: [Deshaun Watson, positionStyle, dual-threat quarterback]
-
A.
stylePositioning
Indicates how an entity is spatially or visually arranged or aligned relative to a reference frame or other elements.
-
B.
positioning
Indicates the spatial or contextual arrangement of one entity relative to another or within a given environment.
-
C.
positionOn
Indicates that one entity is located on top of or at a specific place along the surface or extent of another entity.
-
D.
positionUse
Indicates how a particular position or role is utilized or functionally applied within a given context.
-
E.
positioningStatement
Indicates a relationship where a statement defines how something is uniquely positioned or framed relative to alternatives or a target context.
- 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_69c688143bfc81908d4176617735e601 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea552a688190a00f5d0ad982f787 |
completed | March 27, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69c6e7644648819096a5e2de5d0dbe97 |
completed | March 27, 2026, 8:24 p.m. |
| PDg | Predicate description generation | batch_69c6ea539f5c81908001524149903559 |
completed | March 27, 2026, 8:36 p.m. |
Created at: March 27, 2026, 2:55 p.m.