Triple
T38115266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Touch-a, Touch-a, Touch-a, Touch Me |
E951770
|
entity |
| Predicate | performedToCharacter |
P42947
|
FINISHED |
| Object | Rocky Horror |
—
|
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: Rocky Horror | Statement: [Touch-a, Touch-a, Touch-a, Touch Me, performedToCharacter, Rocky Horror]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedToCharacter Context triple: [Touch-a, Touch-a, Touch-a, Touch Me, performedToCharacter, Rocky Horror]
-
A.
performedForCharacterPortrayedBy
Indicates that an action or performance was carried out for the benefit of a fictional character as portrayed by a specific actor.
-
B.
performedByCharacterType
Indicates that an action or event is carried out by a character belonging to a specified character type or category.
-
C.
performedTo
chosen
Indicates that an action or performance is directed toward or carried out on a particular entity.
-
D.
originalPerformerCharacter
Indicates that a performer is the first or primary actor to portray a particular character in a work.
-
E.
performedTextBy
Indicates that a text-based work (such as a script, lyrics, or written piece) is realized or executed as a performance by a specific performer or group.
- 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_69f76f07734c8190814e937e12257a78 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ff64b957bc81908afbc5914234a8ea |
completed | May 9, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69ff6446593c81909173e296eea2590c |
completed | May 9, 2026, 4:43 p.m. |
Created at: May 3, 2026, 4:21 p.m.