Triple
T27461442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Cavalry vs. Apaches |
E692755
|
entity |
| Predicate | oftenPortrays |
P18297
|
FINISHED |
| Object | Apache warriors as antagonists |
—
|
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: Apache warriors as antagonists | Statement: [U.S. Cavalry vs. Apaches, oftenPortrays, Apache warriors as antagonists]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenPortrays Context triple: [U.S. Cavalry vs. Apaches, oftenPortrays, Apache warriors as antagonists]
-
A.
oftenDepictedAs
chosen
Indicates that one entity is frequently represented or portrayed in the form, appearance, or symbolism of another entity.
-
B.
occasionallyPortrayedAs
Indicates that one entity is sometimes depicted or represented as another entity, but not consistently or as its primary form.
-
C.
typicallyDepicts
Indicates that one entity is most commonly or characteristically portrayed or represented by the other in depictions or images.
-
D.
portraysPersonAs
Indicates that one entity represents, depicts, or characterizes another person in a particular way or role.
-
E.
oftenDescribes
Indicates that one entity is frequently used to characterize, depict, or provide information about 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_69ef5207903881909427745cda05d27a |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f6c49627908190b3553474c7c3072b |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f23ae081909a52801266063a3c |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 27, 2026, 12:50 p.m.