Triple
T23061938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prix Lumières for Best Actor |
E574926
|
entity |
| Predicate | presentedAtFrequency |
P88910
|
FINISHED |
| Object | annually |
—
|
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: annually | Statement: [Prix Lumières for Best Actor, presentedAtFrequency, annually]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: presentedAtFrequency Context triple: [Prix Lumières for Best Actor, presentedAtFrequency, annually]
-
A.
exhibitionFrequency
chosen
Indicates how often an entity is displayed, presented, or exhibited within a given context or time period.
-
B.
performedFrequency
Indicates how often an action or activity is carried out within a given time period.
-
C.
presentedAtTime
Indicates that an event, action, or item was presented or occurred at a specific point in time.
-
D.
presentsAt
Indicates that one entity delivers or gives a presentation, talk, or performance at a particular event, venue, or occasion.
-
E.
presentedOn
Indicates that something (such as information, a work, or a performance) is shown, displayed, or delivered on a particular medium, platform, or occasion.
- 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f189a0c3c881909f137ad511c216ac |
completed | April 29, 2026, 4:31 a.m. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:55 p.m.