Triple
T17973527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Two-Face |
E449405
|
entity |
| Predicate | occupationBeforeDisfigurement |
P28984
|
FINISHED |
| Object | Gotham City district attorney |
—
|
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: Gotham City district attorney | Statement: [Two-Face, occupationBeforeDisfigurement, Gotham City district attorney]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occupationBeforeDisfigurement Context triple: [Two-Face, occupationBeforeDisfigurement, Gotham City district attorney]
-
A.
earlierOccupation
chosen
Indicates that one occupation held by an entity occurred before another occupation in that entity’s work history.
-
B.
resumedOccupation
Indicates that an entity has returned to and continued a previous occupation or role after a period of interruption or absence.
-
C.
hasPastOccupation
Indicates that an entity previously held a particular job, role, or occupation in the past.
-
D.
victimOccupation
Indicates the profession or job role held by the person who is the victim in an event or incident.
-
E.
subjectOccupation
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b1fca04481908f0dd875953fd82f |
completed | April 19, 2026, 10:44 a.m. |
| PD | Predicate disambiguation | batch_69e3f8fa62688190a5d5c361ab896256 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:22 a.m.