Triple
T20053593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zach Cherry |
E499267
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Crashing |
—
|
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: Crashing | Statement: [Zach Cherry, notableWork, Crashing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crashing Context triple: [Zach Cherry, notableWork, Crashing]
-
A.
Crashing
Crashing is a British comedy-drama television series created by and starring Phoebe Waller-Bridge, following a group of twenty-somethings living as property guardians in a disused hospital.
-
B.
Crashing
chosen
Crashing is a semi-autobiographical comedy television series created by and starring Pete Holmes that follows an aspiring stand-up comedian rebuilding his life after his marriage falls apart.
-
C.
CRASH
CRASH was a specialized Los Angeles Police Department anti-gang unit focused on combating street gang activity in the city.
-
D.
Crashing Down
"Crashing Down" is a lesser-known track released as the B-side to the single "Up."
-
E.
Crashout
Crashout is a 1955 American film noir crime drama about a group of escaped convicts on a violent quest for hidden loot.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6633043a481908359ad232607182a |
completed | April 20, 2026, 5:32 p.m. |
Created at: April 11, 2026, 3:38 p.m.