Triple
T8122261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Mack |
E189636
|
entity |
| Predicate | knownFor |
P22
|
FINISHED |
| Object | Would I Lie to You? |
E408612
|
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: Would I Lie to You? | Statement: [Lee Mack, knownFor, Would I Lie to You?]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Would I Lie to You? Context triple: [Lee Mack, knownFor, Would I Lie to You?]
-
A.
"Would I Lie to You?"
chosen
"Would I Lie to You?" is a song by the Eurythmics that serves as the energetic opening theme for the television series Drop Dead Diva.
-
B.
Which Lie Did I Tell?
"Which Lie Did I Tell?" is William Goldman’s follow-up memoir on screenwriting, offering candid, humorous insights into Hollywood and the craft of writing for film.
-
C.
Telling Lies
Telling Lies is an interactive narrative video game that uses full-motion video and a non-linear search-based interface to unravel a complex story through secretly recorded conversations.
-
D.
No Lie
"No Lie" is a popular hip-hop single by 2 Chainz featuring Drake, known for its catchy hook and heavy bass production.
-
E.
No Lie
"No Lie" is a 2016 dancehall-pop single by Jamaican artist Sean Paul featuring Dua Lipa, known for its catchy hook and international chart success.
- 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_69ca82bb74848190afb1f18640632c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb435cb30881909ccaa2f625e53799 |
completed | March 31, 2026, 3:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc945c743c8190bf1d8e60975bd8bc |
completed | April 1, 2026, 3:43 a.m. |
Created at: March 30, 2026, 5:33 p.m.