Triple
T36347801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Rebel Princess |
E895111
|
entity |
| Predicate | firstTelevisionStarringRoleFor |
P170226
|
FINISHED |
| Object | Zhang Ziyi |
E258322
|
NE 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: Zhang Ziyi | Statement: [The Rebel Princess, firstTelevisionStarringRoleFor, Zhang Ziyi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstTelevisionStarringRoleFor Context triple: [The Rebel Princess, firstTelevisionStarringRoleFor, Zhang Ziyi]
-
A.
portrayedInFirstTalkingRoleOf
Indicates that an entity portrayed a character in another entity’s first role in a talking (sound) production.
-
B.
screenDebutInMajorRoleFor
Indicates that one entity made their first significant on-screen appearance (major role) in a particular production or work.
-
C.
televisionRoleStart
Indicates the point in time when an entity begins performing or holding a particular role on a television production.
-
D.
leadActorDebutFilmFor
Indicates that a person’s first film as a lead actor is the specified movie.
-
E.
televisionDebutWith
chosen
Indicates the relationship in which an entity makes its first appearance on television in association with a particular work, program, or context.
- F. None of above.
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_69f76e4f437c8190a1af3ea2564f41f5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3e1608c1808190a7b7b658e50003db |
completed | June 26, 2026, 6:02 a.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.