Triple
T19734654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Kaye |
E473944
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Pulling |
—
|
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: Pulling | Statement: [Paul Kaye, workedOn, Pulling]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pulling Context triple: [Paul Kaye, workedOn, Pulling]
-
A.
Pulling
chosen
Pulling is a British television comedy series known for its darkly humorous portrayal of three single women navigating chaotic relationships and adulthood.
-
B.
Puller
Puller is a surname most prominently associated with the decorated U.S. Marine Corps officer Lewis B. "Chesty" Puller and his family.
-
C.
Push and Pull
"Push and Pull" is a funk and soul song by American singer Rufus Thomas, best known for its infectious groove and popularity in the early 1970s.
-
D.
Pull It
"Pull It" is a hip hop single by rapper Cam'ron from his debut studio album "Confessions of Fire."
-
E.
Traction
Traction is the common nickname for the Citroën Traction Avant, a pioneering French automobile famous for its early use of front-wheel drive and unitary body construction.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6515d138c8190a4c4d112ed5756a3 |
completed | April 20, 2026, 4:16 p.m. |
Created at: April 10, 2026, 1:47 p.m.