Triple
T3915079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Camerimage |
E88815
|
entity |
| Predicate | invites |
P25673
|
FINISHED |
| Object | renowned cinematographers |
—
|
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: renowned cinematographers | Statement: [Camerimage, invites, renowned cinematographers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: invites Context triple: [Camerimage, invites, renowned cinematographers]
-
A.
invitesParticipationOf
chosen
Indicates that one entity actively requests or encourages another entity to take part in an activity, event, or process.
-
B.
invitesResponseOf
Indicates that one entity’s action, message, or state prompts, elicits, or calls for a response from another entity.
-
C.
invitesToBunker
Indicates that one entity extends an invitation to another entity to come to or enter a bunker.
-
D.
isInvited
Indicates that one entity has extended an invitation to another entity to participate in or attend something.
-
E.
invitedOpponents
Indicates that one entity extended an invitation to another entity specifically in the context of being opponents, such as in a match, contest, or competitive event.
- 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_69aed955229881909e85e73ffab1d343 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef188b474819087680db42b04ecdd |
completed | March 9, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69aee75eedcc81908088ff4dbb8be56b |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:22 p.m.