Triple
T34018218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penelope Taynt |
E872306
|
entity |
| Predicate | targetOfObsession |
P860
|
FINISHED |
| Object | Amanda Bynes (character on The Amanda Show) |
—
|
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: Amanda Bynes (character on The Amanda Show) | Statement: [Penelope Taynt, targetOfObsession, Amanda Bynes (character on The Amanda Show)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetOfObsession Context triple: [Penelope Taynt, targetOfObsession, Amanda Bynes (character on The Amanda Show)]
-
A.
obsessionWith
Indicates an intense, persistent, and often overwhelming preoccupation or fixation that one entity has toward another entity or object.
-
B.
target
chosen
Indicates that one entity is the intended object, goal, or focus of another entity’s action or attention.
-
C.
targetOfDeception
Indicates that one entity is being deceived, misled, or tricked by another entity.
-
D.
targetOfAntagonists
Indicates that the referenced entity is the object or focus of hostile actions, opposition, or conflict initiated by antagonistic parties.
-
E.
aimedAtBy
Indicates that one entity serves as the target or goal toward which another entity directs an action, intention, or focus.
- 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_69f349a19ad88190ab586f010c804a8f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fe96c2647c819082989f11e1ae3d35 |
completed | May 9, 2026, 2:06 a.m. |
| PD | Predicate disambiguation | batch_69fe928615448190af939e5a94be55bb |
completed | May 9, 2026, 1:48 a.m. |
Created at: May 1, 2026, 1:51 a.m.