Triple
T24653855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flora Cameron |
E610331
|
entity |
| Predicate | pursuerDescription |
P156918
|
FINISHED |
| Object | Black man portrayed as a threat in the film |
—
|
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: Black man portrayed as a threat in the film | Statement: [Flora Cameron, pursuerDescription, Black man portrayed as a threat in the film]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pursuerDescription Context triple: [Flora Cameron, pursuerDescription, Black man portrayed as a threat in the film]
-
A.
partialPursuer
Indicates that one entity is attempting to pursue or chase another, but only to a limited, incomplete, or non-exclusive extent.
-
B.
pursuingCharacter
Indicates that one character is actively chasing, seeking, or attempting to catch or reach another character.
-
C.
chases
Indicates that one entity actively pursues another, typically moving after it in an attempt to catch or reach it.
-
D.
pursuitLocomotive
Indicates engaging in locomotion specifically aimed at following or chasing another entity.
-
E.
pursuitLocation
Indicates the place or setting where a pursuit or chase between entities occurs.
- F. None of above. chosen
Provenance (4 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_69e2c4d453248190a020354e93ef6282 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f41011d8048190be70329ba0bfb7c7 |
completed | May 1, 2026, 2:29 a.m. |
| PD | Predicate disambiguation | batch_69f40ed9d47881909fcfc0d04e8d074a |
completed | May 1, 2026, 2:24 a.m. |
| PDg | Predicate description generation | batch_69f41010f06c81908ee7f773220df14f |
completed | May 1, 2026, 2:29 a.m. |
Created at: April 18, 2026, 2:34 a.m.