Triple
T28090988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norm Spellman |
E709951
|
entity |
| Predicate | hasAvatarBody |
P159133
|
FINISHED |
| Object | Norm's avatar |
—
|
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: Norm's avatar | Statement: [Norm Spellman, hasAvatarBody, Norm's avatar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAvatarBody Context triple: [Norm Spellman, hasAvatarBody, Norm's avatar]
-
A.
haveBody
Indicates that one entity possesses, contains, or is associated with another entity as its body or main physical/content component.
-
B.
hasBodySwapWith
Indicates a reciprocal relationship where two entities have exchanged bodies or physical forms with each other.
-
C.
isLinkedToAvatar
chosen
Indicates that one entity is associated or connected to a specific avatar representation of a user or character.
-
D.
hasBodyImageIssue
Indicates that an entity experiences concerns, dissatisfaction, or negative perceptions about their own body or physical appearance.
-
E.
hasBodyOf
Indicates that one entity possesses, contains, or is composed of the physical body or main substance of another entity.
- 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_69ef9b70fd108190a875953b2e50ca91 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f64069d75881908f0e93d1c7c66891 |
completed | May 2, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 8:58 p.m.