Triple
T32874282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Babouk |
E840880
|
entity |
| Predicate | hasFictionalizedAccountOf |
P93172
|
FINISHED |
| Object | Haitian Revolution |
—
|
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: Haitian Revolution | Statement: [Babouk, hasFictionalizedAccountOf, Haitian Revolution]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalizedAccountOf Context triple: [Babouk, hasFictionalizedAccountOf, Haitian Revolution]
-
A.
hasFictionalAlias
Indicates that an entity is known by an alternative name or identity within a fictional context.
-
B.
hasFictionalAlterEgoOf
Indicates that one entity is the fictional alter ego, persona, or alternate identity of another entity.
-
C.
hasFictionalAddressee
Indicates that an entity (such as a text or communication) is directed toward or addressed to an addressee that is fictional rather than a real person or audience.
-
D.
hasFictionalBackstory
chosen
Indicates that an entity is associated with an invented or imaginary narrative background rather than a real-world history.
-
E.
isFictionalAgentOf
Indicates that one entity is a fictional character or agent that acts on behalf of, or represents, another entity.
- 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_69f349436ee88190b72ee12d0f3f508e |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fef3ceef648190b58027c93d757438 |
completed | May 9, 2026, 8:43 a.m. |
| PD | Predicate disambiguation | batch_69fef359da2c819091a034387b08821f |
completed | May 9, 2026, 8:42 a.m. |
Created at: May 1, 2026, 1:18 a.m.