Triple
T26876429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBS |
E676762
|
entity |
| Predicate | hasProducerCharacter |
P121021
|
FINISHED |
| Object | Danny Tripp |
—
|
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: Danny Tripp | Statement: [NBS, hasProducerCharacter, Danny Tripp]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProducerCharacter Context triple: [NBS, hasProducerCharacter, Danny Tripp]
-
A.
hasProducer
Indicates that one entity serves as the producer or creator responsible for making or manufacturing another entity.
-
B.
hasFictionalProducer
Indicates that an entity is associated with a producer who exists only as a fictional or imaginary character, not a real person.
-
C.
hasProduction
Indicates that an entity is associated with, or responsible for, the creation or manufacture of another entity or product.
-
D.
producedByCharacter
chosen
Indicates that something (such as a work, item, or outcome) is created or generated by a particular character.
-
E.
hasWriterCharacter
Indicates that a writer is a character within a work, linking the work to the character who serves as its writer.
- 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_69eee9bb44988190b6e11652d028bc59 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69fd5f29b1988190877764ef2a399c7f |
completed | May 8, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69fd5e30194c819085b5ce586122ab37 |
completed | May 8, 2026, 3:53 a.m. |
Created at: April 27, 2026, 5:36 a.m.