Triple
T25395215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madhumati |
E636271
|
entity |
| Predicate | leadActorForCharacterDevinder |
P9616
|
FINISHED |
| Object | Dilip Kumar |
—
|
NE NERFINISHED |
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: Dilip Kumar | Statement: [Madhumati, leadActorForCharacterDevinder, Dilip Kumar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leadActorForCharacterDevinder Context triple: [Madhumati, leadActorForCharacterDevinder, Dilip Kumar]
-
A.
directorCharacterOf
Indicates that a director is responsible for directing a particular character in a work (e.g., film, TV show, or play).
-
B.
playedBy
chosen
Indicates that a role, character, or performance is portrayed or executed by a specific person or agent.
-
C.
directorCharacterName
Indicates that the specified name is the character name used by the director (or representing the director) within a work.
-
D.
leadCharacterCaste
Indicates that the lead character in a work belongs to a specified caste.
-
E.
leadActorOfAdaptation
Indicates that a person is the main actor in a specific adaptation of a work (such as a film, series, or stage version).
- 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_69e75db263888190b77fff9e2827b9a2 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f584f07b648190aee894c1d5320bc3 |
completed | May 2, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:49 p.m.