Triple
T23897848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tim Kang |
E600953
|
entity |
| Predicate | portrayedProfessionOfCharacter |
P153983
|
FINISHED |
| Object | California Bureau of Investigation agent |
—
|
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: California Bureau of Investigation agent | Statement: [Tim Kang, portrayedProfessionOfCharacter, California Bureau of Investigation agent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayedProfessionOfCharacter Context triple: [Tim Kang, portrayedProfessionOfCharacter, California Bureau of Investigation agent]
-
A.
portrayedByProfession
Indicates that an entity is depicted or represented by someone acting in a specified professional capacity.
-
B.
portraysProfession
Indicates that one entity depicts or represents another entity in a specific profession or occupational role.
-
C.
portrayedByWork
Indicates that a work (such as a film, book, or artwork) depicts, represents, or portrays a particular entity.
-
D.
portraysInWork
Indicates that one entity depicts, represents, or plays the role of another entity within a specific creative work.
-
E.
portrayedInWorkType
Indicates that an entity is depicted or represented within a work of a specified type (such as a film, book, painting, or other creative medium).
- 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_69e295341ac0819080647f2908af793c |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cddb3fdc819096dc84a1774d9bee |
completed | April 29, 2026, 9:22 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f167dca3608190ace9d2eef56b2af6 |
completed | April 29, 2026, 2:07 a.m. |
Created at: April 17, 2026, 8:25 p.m.