Triple
T28668525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Candyman |
E725643
|
entity |
| Predicate | hasLegacySequel |
P1961
|
FINISHED |
| Object | Candyman (2021 film) |
—
|
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: Candyman (2021 film) | Statement: [Candyman, hasLegacySequel, Candyman (2021 film)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLegacySequel Context triple: [Candyman, hasLegacySequel, Candyman (2021 film)]
-
A.
hasSequel
chosen
Indicates that one work is followed by another work that continues its story, timeline, or thematic development.
-
B.
hasSequelType
Indicates that one work has a sequel of a specified type or category in relation to another work.
-
C.
hasSequelPiece
Indicates that one creative work is a subsequent installment or continuation that follows another work in a series.
-
D.
hasSecondSequel
Indicates that an entity has a second sequel, i.e., a third work in a series that continues its storyline or content.
-
E.
hasSequelDepiction
Indicates that one depiction of something is followed by another depiction that continues its story 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_69f01d85be388190b669a0e401e2f2c4 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
Created at: April 28, 2026, 5:02 a.m.