Triple
T17756152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taira no Shigemori |
E443244
|
entity |
| Predicate | roleInConflicts |
P6060
|
FINISHED |
| Object | Taira commander |
—
|
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: Taira commander | Statement: [Taira no Shigemori, roleInConflicts, Taira commander]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInConflicts Context triple: [Taira no Shigemori, roleInConflicts, Taira commander]
-
A.
roleInWarOrConflict
Indicates the specific function, position, or involvement an entity has within a particular war or conflict.
-
B.
conflictRole
chosen
Indicates that an entity plays a specific role or position within a conflict or dispute between parties.
-
C.
formedInConflict
Indicates that an entity came into existence as a direct result of, or during the course of, a specific conflict or war.
-
D.
partnerInConflictWith
Indicates that two entities are engaged as opposing partners or sides within the same conflict or dispute.
-
E.
hasPartOfConflict
Indicates that one conflict includes another conflict as a constituent or subordinate part of it.
- 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_69d8b9edf16c8190a59ebd245d378f4f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4841f29f08190b1a1e9624d88120f |
completed | April 19, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69e3cde9dc288190af0e2198487f2051 |
completed | April 18, 2026, 6:31 p.m. |
Created at: April 10, 2026, 10:10 a.m.