Triple
T21994520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Witch from Rapunzel |
E543170
|
entity |
| Predicate | relationshipToRapunzel |
P115760
|
FINISHED |
| Object | captor |
—
|
LITERAL 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: captor | Statement: [Witch from Rapunzel, relationshipToRapunzel, captor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToRapunzel Context triple: [Witch from Rapunzel, relationshipToRapunzel, captor]
-
A.
relationshipToPrincess
Indicates the specific familial, social, or romantic connection that one entity has to a princess.
-
B.
relationshipToMickey
Indicates the specific familial, social, or other personal connection that one entity has to Mickey.
-
C.
roleInTangled
chosen
Indicates that an entity has a specific role or function within the context of "Tangled" (e.g., the film, story, or related production).
-
D.
relationToBabo
Indicates a relationship or connection that an entity has to the person or entity referred to as "Babo."
-
E.
relationshipToQueenOfHearts
Indicates the specific familial, social, or hierarchical relationship that one entity has to the Queen of Hearts.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127639bf48190800b3fa3c1527983 |
completed | April 28, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69e6f6154e408190acc5b2c278acaff4 |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:18 p.m.