Triple
T14514086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | El Topo |
E340471
|
entity |
| Predicate | firstScreenedAs |
P114540
|
FINISHED |
| Object | midnight movie in New York City |
—
|
LITERAL 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: midnight movie in New York City | Statement: [El Topo, firstScreenedAs, midnight movie in New York City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstScreenedAs Context triple: [El Topo, firstScreenedAs, midnight movie in New York City]
-
A.
firstScreeningEvent
Indicates the event representing the earliest or initial screening occurrence associated with an entity.
-
B.
firstScreeningLocation
Indicates the location where something (such as a person, item, or case) is initially screened or evaluated for the first time.
-
C.
firstScreeningYear
Indicates the year in which an entity (such as a film or show) was first publicly screened or premiered.
-
D.
hasScreened
Indicates that one entity has shown, displayed, or evaluated another entity, typically in the context of presenting media or conducting a review or check.
-
E.
firstPerformedAs
Indicates the initial occasion or context in which an entity (such as a work, role, or piece) was performed by a particular performer or group.
- F. None of above. chosen
Provenance (4 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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de9a6d82988190b6f957012bcc63d4 |
completed | April 14, 2026, 7:50 p.m. |
| PD | Predicate disambiguation | batch_69de5c4ccba08190a988bfda0bc9f5cb |
completed | April 14, 2026, 3:25 p.m. |
| PDg | Predicate description generation | batch_69de5fb4de14819092acdecbd201d672 |
completed | April 14, 2026, 3:39 p.m. |
Created at: April 10, 2026, 1:21 a.m.