Triple
T28129203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minamoto no Yoshinaka |
E711014
|
entity |
| Predicate | companionInBattle |
P140399
|
FINISHED |
| Object | Tomoe Gozen |
—
|
NE NERFINISHED |
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: Tomoe Gozen | Statement: [Minamoto no Yoshinaka, companionInBattle, Tomoe Gozen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: companionInBattle Context triple: [Minamoto no Yoshinaka, companionInBattle, Tomoe Gozen]
-
A.
partnerInBattle
chosen
Indicates that two entities are allied or cooperate as partners in the same battle or combat engagement.
-
B.
companionOf
Indicates that one entity serves as a companion or partner to another, typically accompanying or being closely associated with them.
-
C.
wasCompanionOf
Indicates that one entity accompanied or associated closely with another, typically as a partner, ally, or fellow participant over some period of time.
-
D.
hasNumberOfCompanions
Indicates the quantity of companions or associates that an entity has.
-
E.
associatedWithBattle
Indicates a relationship where an entity is connected or linked to a specific battle, such as by participation, relevance, or involvement.
- 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_69ef9b73bd288190a21ae3d6aa14f386 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6c1265c208190aacd2b551f8f0f82 |
completed | May 3, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2415fc81908c23c311aebce66f |
completed | May 3, 2026, 3:12 a.m. |
Created at: April 27, 2026, 9:22 p.m.