Triple
T28244503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casey Stuart |
E712126
|
entity |
| Predicate | bringsToLife |
P114391
|
FINISHED |
| Object | Eve (fashion doll) |
—
|
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: Eve (fashion doll) | Statement: [Casey Stuart, bringsToLife, Eve (fashion doll)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bringsToLife Context triple: [Casey Stuart, bringsToLife, Eve (fashion doll)]
-
A.
givesLifeTo
chosen
Indicates a relationship where one entity causes, enables, or sustains the existence, vitality, or functioning of another.
-
B.
broughtTo
Indicates that one entity caused another entity or object to be transported or accompanied to a particular destination or recipient.
-
C.
broughtBack
Indicates that an entity caused another entity to return to a previous place, state, or condition.
-
D.
isToyToLifeFigure
Indicates that an object is a physical toy figure designed to be digitally activated or used within a video game or virtual environment.
-
E.
publicLife
Indicates that an entity is involved in activities, roles, or interactions that are conducted openly in the public sphere rather than in private life.
- 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_69efb51fb98881909692421959ec0170 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f643c77edc8190bb23727297adb769 |
completed | May 2, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69f63c6c1a948190b68c0f92c264cc0c |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 11 p.m.