Triple
T17907845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mac |
E447746
|
entity |
| Predicate | imaginaryFriendType |
P95848
|
FINISHED |
| Object | human child with imaginary friend |
—
|
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: human child with imaginary friend | Statement: [Mac, imaginaryFriendType, human child with imaginary friend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: imaginaryFriendType Context triple: [Mac, imaginaryFriendType, human child with imaginary friend]
-
A.
hasImaginaryFriendCharacter
chosen
Indicates that an entity is associated with or has an imaginary friend character.
-
B.
imaginaryEnemy
Indicates that one entity regards another as an enemy that exists only in imagination rather than in reality.
-
C.
typeOfCharacter
Indicates that one entity is a specific kind or category of character in relation to another entity.
-
D.
semiAutobiographicalCharacter
Indicates that a character is based partly on the real-life experiences, personality, or identity of its creator or author, but is not a fully direct self-portrayal.
-
E.
isFriendOfProtagonist
Indicates that one entity is a friend or close ally of the story’s main character.
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49e9d458881909e35e1c7a6e85436 |
completed | April 19, 2026, 9:21 a.m. |
| PD | Predicate disambiguation | batch_69e3d8ec2f6881909d7f54b878cbed37 |
completed | April 18, 2026, 7:18 p.m. |
Created at: April 10, 2026, 10:19 a.m.