Triple
T12393124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | El Duque |
E296045
|
entity |
| Predicate | careerPhase |
P19243
|
FINISHED |
| Object | late 1990s Yankees |
—
|
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: late 1990s Yankees | Statement: [El Duque, careerPhase, late 1990s Yankees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: careerPhase Context triple: [El Duque, careerPhase, late 1990s Yankees]
-
A.
partOfCareer
chosen
Indicates that one entity represents a role, position, or period that forms a component or phase within another entity’s overall career.
-
B.
careerStatus
Indicates the current stage, position, or condition of an entity within its professional or occupational life.
-
C.
careerStart
Indicates the point in time when an entity begins its professional career or main occupational activity.
-
D.
laterCareer
Indicates that the associated information or events pertain to a later stage or phase in an entity’s professional life or career trajectory.
-
E.
careerPath
Indicates the progression or sequence of roles, positions, or occupations that an individual follows over time in their professional life.
- 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fd228488190b216abd1c341563c |
completed | April 10, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69d93ed256788190b704cad171a4824e |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.