Triple
T4356096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Die Hard |
E98150
|
entity |
| Predicate | villainAffiliation |
P50207
|
FINISHED |
| Object | German terrorists posing as thieves |
—
|
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: German terrorists posing as thieves | Statement: [Die Hard, villainAffiliation, German terrorists posing as thieves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: villainAffiliation Context triple: [Die Hard, villainAffiliation, German terrorists posing as thieves]
-
A.
villainOrganization
chosen
Indicates that an entity is an organization characterized as antagonistic, criminal, or evil within a given context or narrative.
-
B.
hasVillain
Indicates that one entity is the villain or primary antagonist associated with another entity.
-
C.
villainDescription
Indicates that one entity provides a description or characterization of a villainous role or antagonist associated with another entity.
-
D.
antagonistOccupation
Indicates the role, job, or professional activity that the antagonist character performs.
-
E.
featuresVillainActor
Indicates that the subject includes or presents an actor in the role of a villain.
- 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_69b3454965f881908c41190bb22f0e4b |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b351c5773481908446d84897e7a533 |
completed | March 12, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69b34f51ed7c8190b7bf5f44b56b730d |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:16 p.m.