Triple
T27540615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanji’s Oresama Restaurant |
E695222
|
entity |
| Predicate | notableCharacterFocus |
P77485
|
FINISHED |
| Object | Sanji |
—
|
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: Sanji | Statement: [Sanji’s Oresama Restaurant, notableCharacterFocus, Sanji]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableCharacterFocus Context triple: [Sanji’s Oresama Restaurant, notableCharacterFocus, Sanji]
-
A.
notableCharacterType
Indicates that an entity is a notable or prominent example of a specified character type or role.
-
B.
notableCharacterName
Indicates that the subject has a notable or significant character whose name is given by the object.
-
C.
notableCharacterGroup
Indicates that a group of characters is especially prominent, significant, or noteworthy within a given context or work.
-
D.
notableSeriesCharacter
Indicates that an entity is a significant or well-known character appearing in a particular series.
-
E.
characterInFocus
chosen
Indicates that a particular character is the primary subject or focal point within a given context, scene, or narrative segment.
- 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_69ef5386c3e08190bfe33aa326e1f72b |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69ffecdcbac4819093b725a7dbe0e61b |
completed | May 10, 2026, 2:26 a.m. |
| PD | Predicate disambiguation | batch_69ffec3633288190adbbd84e277708dc |
completed | May 10, 2026, 2:23 a.m. |
Created at: April 27, 2026, 1:30 p.m.