Triple
T28958830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elastic Heart (featuring Maddie Ziegler) |
E731835
|
entity |
| Predicate | mainDancer |
P139890
|
FINISHED |
| Object | Maddie Ziegler |
—
|
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: Maddie Ziegler | Statement: [Elastic Heart (featuring Maddie Ziegler), mainDancer, Maddie Ziegler]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainDancer Context triple: [Elastic Heart (featuring Maddie Ziegler), mainDancer, Maddie Ziegler]
-
A.
mainDance
Indicates that an entity performs or is associated with the primary or central dance in a given context or event.
-
B.
mainPerformer2
Indicates that an entity serves as a primary or lead performer in relation to a specific event, work, or performance, typically as a second recorded main performer role.
-
C.
mainRite
Indicates that one ritual, ceremony, or rite is the primary or central rite associated with a given context, entity, or event.
-
D.
featuredDancers
chosen
Indicates that certain dancers are highlighted or given special prominence in a performance, event, or context.
-
E.
firstAuroraDancer
Indicates that an entity is the first individual to perform or embody the role of an Aurora Dancer in a given context or sequence.
- 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_69f043ee242c8190b063248b417c5a69 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 8:49 a.m.