Triple
T21943742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pondicherry Zoo |
E541884
|
entity |
| Predicate | employerOfInFiction |
P93486
|
FINISHED |
| Object | Pi Patel's family |
—
|
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: Pi Patel's family | Statement: [Pondicherry Zoo, employerOfInFiction, Pi Patel's family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employerOfInFiction Context triple: [Pondicherry Zoo, employerOfInFiction, Pi Patel's family]
-
A.
employerInPlot
chosen
Indicates that one entity serves as the employer of another within the context of a specific plot or storyline.
-
B.
employerInUniverse
Indicates that one entity serves as the employer of another within a specified universe, context, or world.
-
C.
officeAssumedInFiction
Indicates that an entity is depicted as assuming or taking on an office or official position within a fictional context or narrative.
-
D.
worksForFictionalOrganization
Indicates that an entity is employed by or affiliated as a worker with a fictional organization.
-
E.
workLocationOfFictionalCharacter
Indicates the place or organization where a fictional character is depicted as working within their narrative 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1242515ec8190b015bf8c7b13be85 |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:56 p.m.