Triple
T30417992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Candy |
E773811
|
entity |
| Predicate | isCharacterOfType |
P100139
|
FINISHED |
| Object | room-based fictional character |
—
|
LITERAL FINISHED |
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: room-based fictional character | Statement: [Candy, isCharacterOfType, room-based fictional character]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCharacterOfType Context triple: [Candy, isCharacterOfType, room-based fictional character]
-
A.
hasTypicalCharacterType
Indicates that an entity is commonly associated with or exemplified by a particular type of character or persona.
-
B.
hasCharacterClass
chosen
Indicates that an entity (such as a character) belongs to or is assigned a particular character class or role type.
-
C.
usedForCharacterType
Indicates that something is intended to be used for, or is suitable for, a particular type of character.
-
D.
testsCharacterOf
Indicates that one entity challenges or probes another entity in order to reveal or evaluate that entity’s moral qualities, integrity, or inner nature.
-
E.
isKeyCharacterIn
Indicates that an entity plays a central or primary role as a main or significant character within another entity, such as a story, game, or narrative work.
- 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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6864b4dc08190ba1e8cf98c0b47f4 |
completed | May 2, 2026, 11:18 p.m. |
| PD | Predicate disambiguation | batch_69f678d019fc8190913662cd2f87b857 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 8:05 p.m.