Triple
T19752677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fujiwara no Yasuhira |
E474418
|
entity |
| Predicate | mentionedIn |
P831
|
FINISHED |
| Object | Gikeiki |
—
|
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: Gikeiki | Statement: [Fujiwara no Yasuhira, mentionedIn, Gikeiki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gikeiki Context triple: [Fujiwara no Yasuhira, mentionedIn, Gikeiki]
-
A.
Gikeiki
chosen
Gikeiki is a medieval Japanese war tale that dramatizes the life and exploits of the legendary samurai Minamoto no Yoshitsune.
-
B.
Gekū
Gekū is one of the two main shrines of the Ise Grand Shrine complex in Japan, traditionally dedicated to the Shinto deity of food, clothing, and shelter.
-
C.
Kigensetsu
Kigensetsu was a pre-World War II Japanese national holiday that celebrated the mythical founding of Japan and the divine origins of the emperor.
-
D.
Kaisei
Kaisei is a small town in Kanagawa Prefecture, Japan, known for its residential character and proximity to larger urban centers.
-
E.
Geikie
Geikie is a Scottish surname most notably associated with Archibald Geikie, a prominent 19th-century geologist and director of the British Geological Survey.
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6529bcb8c8190bcca61a53be86757 |
completed | April 20, 2026, 4:21 p.m. |
Created at: April 10, 2026, 1:48 p.m.