Triple
T2624815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madame Secretary |
E59091
|
entity |
| Predicate | mainCharacterFormerOccupation |
P35945
|
FINISHED |
| Object | CIA analyst |
—
|
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: CIA analyst | Statement: [Madame Secretary, mainCharacterFormerOccupation, CIA analyst]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainCharacterFormerOccupation Context triple: [Madame Secretary, mainCharacterFormerOccupation, CIA analyst]
-
A.
characterFormerOccupation
chosen
Indicates that a character previously held a specific occupation but no longer does.
-
B.
earlierOccupation
Indicates that one occupation held by an entity occurred before another occupation in that entity’s work history.
-
C.
featuresProtagonistOccupation
Indicates that the work’s main character has a specified occupation or job role.
-
D.
workedAs
Indicates that an entity held a particular job, role, or position, performing work in that capacity.
-
E.
fictionalOccupation
Indicates that one entity is the imaginary or narrative-based job, role, or profession attributed to another entity within a fictional context.
- 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_69ab4ac558388190962492cd2e1b0ce6 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abdaca581881908fe8d3d820f839b7 |
completed | March 7, 2026, 7:59 a.m. |
| PD | Predicate disambiguation | batch_69abd80f48888190afdf7e3e042157d0 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:50 p.m.