Triple
T28037133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tim Canterbury |
E708439
|
entity |
| Predicate | teases |
P163651
|
FINISHED |
| Object | Gareth Keenan |
—
|
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: Gareth Keenan | Statement: [Tim Canterbury, teases, Gareth Keenan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teases Context triple: [Tim Canterbury, teases, Gareth Keenan]
-
A.
ties
Indicates that one entity fastens, secures, or binds another entity (or two entities together), typically using a flexible connector such as a string, rope, or similar medium.
-
B.
tells
Indicates that one entity communicates information, a message, or a story to another entity.
-
C.
tez
Indicates a relationship or action between entities, but the specific meaning of the predicate "tez" is undefined without additional context.
-
D.
temptation
Indicates a situation or influence that strongly urges or entices an entity to perform an action, typically one that is considered wrong, unwise, or against their better judgment.
-
E.
usesDoubleEntendre
Indicates that one entity employs language or expressions with a double meaning, often to convey a hidden or suggestive message alongside a literal one.
- 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_69ef9b6cf538819094a633ffa67afec1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f63f2d52088190bc5658fadc7a1c3c |
completed | May 2, 2026, 6:15 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f63893cc188190883ac9321a95d2dc |
completed | May 2, 2026, 5:46 p.m. |
Created at: April 27, 2026, 8:22 p.m.