Triple
T29370302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick (The Perks of Being a Wallflower) |
E744834
|
entity |
| Predicate | relationshipDynamicWithBrad |
P203171
|
FINISHED |
| Object | Brad is closeted |
—
|
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: Brad is closeted | Statement: [Patrick (The Perks of Being a Wallflower), relationshipDynamicWithBrad, Brad is closeted]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipDynamicWithBrad Context triple: [Patrick (The Perks of Being a Wallflower), relationshipDynamicWithBrad, Brad is closeted]
-
A.
relationshipStatusWithBrad
Indicates the type or state of the relationship that an entity currently has with Brad.
-
B.
relationshipStatusWithBradSimon
Indicates the type or state of the relationship that an entity currently has with Brad Simon.
-
C.
relationshipStatusWithBrian
Indicates the current nature or state of an entity’s personal relationship with Brian.
-
D.
relationshipWithBlondie
Indicates that there exists some form of relationship or connection between an entity and Blondie.
-
E.
relationshipToTheDude
Indicates the specific type of personal or social relationship that one entity has to the individual referred to as "the Dude."
- F. None of above. chosen
Provenance (4 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_69f0a79ba954819094597628112c6091 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_6a013632a3048190b05716d803f34716 |
completed | May 11, 2026, 1:51 a.m. |
| PD | Predicate disambiguation | batch_6a01309582e48190a05d47d96ffb7a46 |
completed | May 11, 2026, 1:27 a.m. |
| PDg | Predicate description generation | batch_6a013631f4d48190b1e79e8ff313d3d2 |
completed | May 11, 2026, 1:51 a.m. |
Created at: April 28, 2026, 2:26 p.m.