Triple
T8628655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hector Williams |
E204341
|
entity |
| Predicate | isFictionalSoldierIn |
P25662
|
FINISHED |
| Object | United States Army special operations (fictional) |
—
|
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: United States Army special operations (fictional) | Statement: [Hector Williams, isFictionalSoldierIn, United States Army special operations (fictional)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFictionalSoldierIn Context triple: [Hector Williams, isFictionalSoldierIn, United States Army special operations (fictional)]
-
A.
hasFictionalRole
chosen
Indicates that an entity plays or is assigned a specific role within a fictional work or narrative.
-
B.
wasProfessionalSoldier
Indicates that an individual served as a professional soldier, engaging in military service as their primary occupation.
-
C.
isFictionalNazi
Indicates that an entity is portrayed as a Nazi within a fictional or narrative context.
-
D.
hasFictionalLeader
Indicates that an entity is led or governed by a leader who is a fictional character rather than a real person.
-
E.
hasSoldier
Indicates that one entity possesses, employs, or is associated with a soldier or group of soldiers.
- 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_69ca834a4ea0819094970dceb9e389f3 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5730309081909a9a0256c9bf5f8f |
completed | March 31, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69cc455906f8819082edd79cb4a1cf28 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:27 p.m.