Triple
T28431075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Would I Lie to You? |
E715129
|
entity |
| Predicate | hasRecurringParticipant |
P139929
|
FINISHED |
| Object | David Mitchell |
—
|
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: David Mitchell | Statement: [Would I Lie to You?, hasRecurringParticipant, David Mitchell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRecurringParticipant Context triple: [Would I Lie to You?, hasRecurringParticipant, David Mitchell]
-
A.
hasRecurringActor
chosen
Indicates that an actor appears repeatedly across multiple instances or episodes within a work or series.
-
B.
hasRecurringRole
Indicates that an entity repeatedly appears or participates in a role within an ongoing or multiple related contexts over time.
-
C.
hasRecurringSpecial
Indicates that an entity regularly offers or features a special deal, item, or promotion that recurs over time.
-
D.
hasParticipants
Indicates that an event, activity, or situation involves one or more entities as participants in it.
-
E.
recurringDuring
Indicates that an event or state happens repeatedly within the time span or context defined by another event or interval.
- 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_69efd6b253888190b3c7222ed6a403a8 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69ff59b33a38819086cc9aa19b81748b |
completed | May 9, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69ff587758f88190a39c2164341dc554 |
completed | May 9, 2026, 3:53 p.m. |
Created at: April 28, 2026, 1:39 a.m.