Triple
T29721327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dance of the Earth |
E752060
|
entity |
| Predicate | associatedWorkPremierePlace |
P112744
|
FINISHED |
| Object | Théâtre des Champs-Élysées, Paris |
E21125
|
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: Théâtre des Champs-Élysées, Paris | Statement: [Dance of the Earth, associatedWorkPremierePlace, Théâtre des Champs-Élysées, Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWorkPremierePlace Context triple: [Dance of the Earth, associatedWorkPremierePlace, Théâtre des Champs-Élysées, Paris]
-
A.
placeOfWorkPremiere
Indicates the location where a person’s work or performance was first publicly presented or debuted.
-
B.
worldPremierePlace
chosen
Indicates the place where something (typically a work or event) was first publicly premiered in the world.
-
C.
workPremiereTheater
Indicates the theater where a work (such as a play, film, or performance) was first publicly premiered.
-
D.
premieredInWorkPremiereYear
Indicates the year in which a work (such as a performance, film, or composition) had its first public premiere.
-
E.
parentWorkPremiereCountry
Indicates the country where the premiere of the parent work (from which this work is derived) took place.
- 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_69f0d628c00c8190ab5ee7e423d7ec3c |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a26e5dec1d0819090154bff36b5110c |
completed | June 8, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_6a0379e0f3d88190a4ee7b0673f1ef90 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 28, 2026, 7:36 p.m.