Triple
T35555578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shannon Plumb |
E1027482
|
entity |
| Predicate | hasScreeningsAt |
P138887
|
FINISHED |
| Object | Museum of Modern Art, New York |
—
|
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: Museum of Modern Art, New York | Statement: [Shannon Plumb, hasScreeningsAt, Museum of Modern Art, New York]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasScreeningsAt Context triple: [Shannon Plumb, hasScreeningsAt, Museum of Modern Art, New York]
-
A.
hasFilmScreenings
Indicates that a film is scheduled to be shown at one or more specific screenings or venues.
-
B.
hasScreening
chosen
Indicates that one entity conducts, hosts, or is associated with a particular screening event involving another entity.
-
C.
screeningsOccurDuring
Indicates that the time period of the screenings takes place within or overlaps with a specified time interval or event.
-
D.
screenedIn
Indicates that one entity has been evaluated or assessed to determine whether it meets certain criteria for inclusion, participation, or further consideration in relation to another entity.
-
E.
screenedOn
Indicates that something (such as a film, show, or content) was shown or broadcast on a particular screen, channel, platform, or date.
- 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_69f76e014fd481909e9f04ac603a2aa9 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd4f39b5008190b83b3227ce22c509 |
completed | May 8, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69fd4df17c548190a4e2a6fea70f7e10 |
completed | May 8, 2026, 2:44 a.m. |
Created at: May 3, 2026, 4:04 p.m.