Triple
T3949748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katherine Kelly |
E84833
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Cheat |
E402813
|
NE 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: Cheat | Statement: [Katherine Kelly, appearedIn, Cheat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cheat Context triple: [Katherine Kelly, appearedIn, Cheat]
-
A.
Cheat
chosen
Cheat is a British psychological thriller television series centered on a tense and escalating conflict between a university lecturer and her seemingly duplicitous student.
-
B.
Trick
Trick is a minor character in the "Arkangel" episode of the anthology television series Black Mirror.
-
C.
Deceive
"Deceive" is a popular Afro-pop song by Nigerian singer Yemi Alade, known for its catchy melody and themes of romantic conflict and mistrust.
-
D.
Chepes
Chepes is a small city in western Argentina that serves as an important local center within La Rioja Province.
-
E.
Hacks
Hacks is a critically acclaimed American comedy-drama television series that explores the professional and personal relationship between a legendary Las Vegas comedian and a young, struggling comedy writer.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed934fbfc8190847068e4546de963 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef91227a8819097c3a5a206792382 |
completed | March 9, 2026, 4:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b53ffc49f48190949d14113031dd85 |
completed | March 14, 2026, 11:01 a.m. |
Created at: March 9, 2026, 3:30 p.m.