Triple
T18289890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shirakawa-tennō |
E438082
|
entity |
| Predicate | eraName |
P2938
|
FINISHED |
| Object | Daiji |
—
|
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: Daiji | Statement: [Shirakawa-tennō, eraName, Daiji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daiji Context triple: [Shirakawa-tennō, eraName, Daiji]
-
A.
Daiji
chosen
Daiji was a Japanese era name (nengō) used during the reign of Emperor Toba in the early 12th century.
-
B.
Savindan
Savindan is the Serbian Orthodox holiday and cultural celebration honoring Saint Sava, the first Archbishop of the Serbian Church and patron of education.
-
C.
Jai
Jai is an Indian actor best known for his work in Tamil cinema, particularly for his breakout performance in the critically acclaimed film "Subramaniapuram."
-
D.
Jai
Jai is the given name of Australian actor Jai Courtney, known for his roles in action and blockbuster films.
-
E.
Daji
Daji is a legendary figure in Chinese mythology, often depicted as a beautiful but malevolent consort whose influence is blamed for the downfall of the Shang dynasty.
- 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e500fd65888190afdbb29dc60066af |
completed | April 19, 2026, 4:21 p.m. |
Created at: April 10, 2026, 10:35 a.m.