Triple
T12238041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abraham Zapruder |
E291651
|
entity |
| Predicate | filmed |
P30539
|
FINISHED |
| Object | assassination of John F. Kennedy |
—
|
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: assassination of John F. Kennedy | Statement: [Abraham Zapruder, filmed, assassination of John F. Kennedy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmed Context triple: [Abraham Zapruder, filmed, assassination of John F. Kennedy]
-
A.
filmedAs
Indicates that an entity was recorded or captured in a particular form, version, or role during a filming or production process.
-
B.
filmedFrom
chosen
Indicates that one entity serves as the physical or conceptual vantage point or recording source from which another entity (such as a scene, object, or event) is filmed.
-
C.
filmedFor
Indicates that something was recorded or produced specifically for a particular purpose, audience, platform, or project.
-
D.
recordedForFilm
Indicates that an audio or performance was captured specifically for use in a film production.
-
E.
filmingState
Indicates the current production or recording status of a filming activity, such as whether it is planned, in progress, paused, or completed.
- 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_69d6ab668acc8190963ba424049d6aee |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d924a3973c8190a882046963b320fb |
completed | April 10, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69d91c41bcbc81909782f4e3c571b218 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.