Triple
T22547042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richter (Total Recall) |
E557455
|
entity |
| Predicate | worksForVillain |
P101668
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Richter (Total Recall), worksForVillain, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksForVillain Context triple: [Richter (Total Recall), worksForVillain, true]
-
A.
hasVillain
Indicates that one entity is the villain or primary antagonist associated with another entity.
-
B.
focusesOnVillain
Indicates that the primary attention, narrative emphasis, or activity is directed toward a villain as the central subject.
-
C.
servesAntagonist
chosen
Indicates that one entity performs actions in support of, under the command of, or to the benefit of an antagonist.
-
D.
antagonistActionOf
Indicates that one entity performs an action in opposition or hostility toward another entity, acting as its antagonist.
-
E.
featuresAntagonistEntity
Indicates that the subject includes or involves an entity serving as an antagonist in the context of a narrative, interaction, or scenario.
- 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_69e11e58662081909ae346ab384514ca |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f366f208190abbc6eb4780b2d48 |
completed | April 29, 2026, 1:30 a.m. |
| PD | Predicate disambiguation | batch_69e898cb3fb48190add6ab24a2df5822 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:52 p.m.