Triple
T37872889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Shado-Pan |
E944647
|
entity |
| Predicate | Shado-Pan AssaultRole |
P4347
|
FINISHED |
| Object | frontline force against the Thunder King |
—
|
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: frontline force against the Thunder King | Statement: [The Shado-Pan, Shado-Pan AssaultRole, frontline force against the Thunder King]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Shado-Pan AssaultRole Context triple: [The Shado-Pan, Shado-Pan AssaultRole, frontline force against the Thunder King]
-
A.
ShuForces
Indicates a relationship where forces or military units are associated with, belong to, or act on behalf of the Shu faction or state.
-
B.
roleInOperation Eagle Claw
Indicates that an entity participated in Operation Eagle Claw in a specified role or capacity.
-
C.
UnionCommanderOfAssault
Indicates that the subject served as the commanding Union officer in charge of a specific military assault.
-
D.
roleInBladeII
Indicates that an entity has a specific role or participation in the movie "Blade II."
-
E.
paramilitaryWing
chosen
Indicates that one entity functions as the paramilitary or armed wing associated with another entity, typically an organization or movement.
- 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_69f76eef55d481908ca6660b4b532550 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbbae559a8819086ef839973f8d9b2 |
completed | May 6, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69fbb1440fa08190abf25ba684f75b6e |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.