Triple
T18378695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ōhime |
E446383
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Minamoto |
—
|
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: Minamoto | Statement: [Ōhime, familyName, Minamoto]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Minamoto Context triple: [Ōhime, familyName, Minamoto]
-
A.
Minamoto
chosen
Minamoto was a powerful Japanese samurai clan that played a central role in the late Heian and early Kamakura periods, producing several shoguns and shaping the rise of the shogunate.
-
B.
Taira
Taira was a powerful samurai clan that dominated late Heian-period Japanese politics and warfare before its downfall in the Genpei War.
-
C.
Matsunaga
Matsunaga is a tubercular yakuza gangster whose tragic decline underpins the gritty postwar drama of Akira Kurosawa’s film "Drunken Angel."
-
D.
Hōjō
Hōjō is the main hall or abbot’s quarters in a Zen Buddhist temple complex, serving as a central space for administration and monastic life.
-
E.
Hōjō
Hōjō was a powerful samurai clan that rose to prominence as feudal lords in Japan during the late Sengoku and early Edo periods.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f370b88190b1e5081c2c238e7f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e5179919c881908d55ea24f93c5827 |
completed | April 19, 2026, 5:57 p.m. |
Created at: April 10, 2026, 10:45 a.m.