Triple
T35484919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karen Patch |
E1025566
|
entity |
| Predicate | designedForActor |
P116845
|
FINISHED |
| Object | Gwyneth Paltrow |
—
|
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: Gwyneth Paltrow | Statement: [Karen Patch, designedForActor, Gwyneth Paltrow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designedForActor Context triple: [Karen Patch, designedForActor, Gwyneth Paltrow]
-
A.
designedForTheatre
Indicates that something was specifically created or intended to be used in a theatre context or theatrical setting.
-
B.
isDesignedFor
Indicates that one entity has been created, planned, or optimized specifically to serve the needs, purposes, or use of another entity.
-
C.
intendedForPerformanceBy
chosen
Indicates that something (such as a work, role, or piece) is designed or meant to be performed by a particular performer or type of performer.
-
D.
actsFor
Indicates that one entity performs actions or exercises authority on behalf of another entity.
-
E.
designedRole
Indicates that one entity has been created, configured, or intended to serve a particular function, purpose, or role in relation to 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_69f76dfbcdd881908c7b0b6bc502252b |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff1a972bf08190860696ffcd887c0f |
completed | May 9, 2026, 11:29 a.m. |
| PD | Predicate disambiguation | batch_69ff184005d88190bf38283ebc499b28 |
completed | May 9, 2026, 11:19 a.m. |
Created at: May 3, 2026, 4:04 p.m.