Triple
T32997229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maria Cantwell |
E844261
|
entity |
| Predicate | hasPreviousOccupation |
P107616
|
FINISHED |
| Object | business executive |
—
|
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: business executive | Statement: [Maria Cantwell, hasPreviousOccupation, business executive]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPreviousOccupation Context triple: [Maria Cantwell, hasPreviousOccupation, business executive]
-
A.
hasPastOccupation
chosen
Indicates that an entity previously held a particular job, role, or occupation in the past.
-
B.
earlierOccupation
Indicates that one occupation held by an entity occurred before another occupation in that entity’s work history.
-
C.
hadOccupationStatusUntil
Indicates that an entity held a particular occupational status up to, but not necessarily beyond, a specified point in time.
-
D.
memberLaterOccupation
Indicates that an individual later held a particular occupation or position after an earlier point in time or role.
-
E.
resumedOccupation
Indicates that an entity has returned to and continued a previous occupation or role after a period of interruption or absence.
- 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_69f3494d99988190b502c68926af2c4d |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a013c50bcb8819086d163f1a796a9b8 |
completed | May 11, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_6a013c01bac88190b15c70910c02a8a7 |
completed | May 11, 2026, 2:16 a.m. |
Created at: May 1, 2026, 1:22 a.m.