Triple
T34823421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carlotta Grisi |
E1003850
|
entity |
| Predicate | originallyPortrayed |
P125509
|
FINISHED |
| Object | Giselle (character) |
E995948
|
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: Giselle (character) | Statement: [Carlotta Grisi, originallyPortrayed, Giselle (character)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originallyPortrayed Context triple: [Carlotta Grisi, originallyPortrayed, Giselle (character)]
-
A.
firstPortrayedBy
Indicates that the subject character or role was originally depicted or played by the specified performer for the first time.
-
B.
firstStagePortrayalBy
Indicates that an entity’s initial or earliest stage is depicted or represented by another entity.
-
C.
originallyAppearedOn
Indicates the original source or platform where something (such as a work, content, or item) was first published, released, or made available.
-
D.
portrayedInOriginalProductionBy
chosen
Indicates that an entity (such as a role or character) was first brought to life or performed in the original production by a specific performer.
-
E.
wasPortrayedAs
Indicates that one entity has been depicted or represented in the form or role of another entity, typically within some medium 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_69f76db717088190811b4e744610f37d |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a376fbba43881909219c2c6a8730cfc |
completed | June 21, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_6a0379ff1ba081908eda86acefcf69fb |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4 p.m.