Triple
T8268098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheldon Cooper |
E193350
|
entity |
| Predicate | favoriteSeat |
P48956
|
FINISHED |
| Object | spot on the couch |
—
|
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: spot on the couch | Statement: [Sheldon Cooper, favoriteSeat, spot on the couch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: favoriteSeat Context triple: [Sheldon Cooper, favoriteSeat, spot on the couch]
-
A.
seatingPosition
Indicates the relative location or arrangement of an entity’s seat with respect to other seats or a reference point in a seating layout.
-
B.
typicalSeat
chosen
Indicates the usual or standard seating position or location associated with an entity in a given context.
-
C.
laterSeat
Indicates that one entity is seated in a position that comes after another entity in a specified ordering or sequence of seats.
-
D.
seatOn
Indicates that one entity is positioned or placed on a seat or seating surface associated with another entity.
-
E.
otherSeat
Indicates that one entity is the alternative or different seat relative to another seat in a given context.
- 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_69ca82e081d48190986beaa51f498ab9 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb794fc4208190b268bc69ff2b28a9 |
completed | March 31, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_69cb70a4525481909399d313a6247ace |
completed | March 31, 2026, 6:58 a.m. |
Created at: March 30, 2026, 5:50 p.m.