Triple
T15357392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The World's Greatest Detective |
E367197
|
entity |
| Predicate | appliedToCharacterType |
P10724
|
FINISHED |
| Object | superhero |
—
|
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: superhero | Statement: [The World's Greatest Detective, appliedToCharacterType, superhero]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliedToCharacterType Context triple: [The World's Greatest Detective, appliedToCharacterType, superhero]
-
A.
followsCharacterType
Indicates that one character’s behavior, role, or traits are patterned after, derived from, or constrained by a specified character type.
-
B.
hasTypicalCharacterType
chosen
Indicates that an entity is commonly associated with or exemplified by a particular type of character or persona.
-
C.
hasCharacterClass
Indicates that an entity (such as a character) belongs to or is assigned a particular character class or role type.
-
D.
capturesCharacter
Indicates that one entity seizes, traps, or takes control of another character.
-
E.
characterCorrespondsTo
Indicates that one character is equivalent to, maps onto, or represents another character in a defined correspondence or mapping.
- 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_69d85a1483788190ad93c2748e8af34b |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e2d4934819097fc63603964217c |
completed | April 16, 2026, 1:41 a.m. |
| PD | Predicate disambiguation | batch_69deca991e5081908b0df3d1ee7d5338 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:18 a.m.