Triple
T23484207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marion Davies |
E570485
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Show People |
—
|
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: Show People | Statement: [Marion Davies, notableWork, Show People]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Show People Context triple: [Marion Davies, notableWork, Show People]
-
A.
Show People
chosen
Show People is a 1928 silent comedy film directed by King Vidor that satirizes Hollywood and the movie industry.
-
B.
People
People is a widely read American weekly magazine focusing on celebrity news, human-interest stories, and popular culture.
-
C.
People
"People" is a song featured on the 2014 album "Partners" by Barbra Streisand.
-
D.
People
"People" is an EP by the experimental pop band Animal Collective, showcasing their distinctive blend of psychedelic and avant-garde sounds.
-
E.
People
People is the legal designation for the collective citizenry of California as a party in criminal and certain civil court cases, representing the public interest through the state.
- 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a752c678819087e5c50b8cf87d3d |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:03 p.m.