Triple
T36366177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lumières de Noël de Montbéliard |
E895630
|
entity |
| Predicate | activitéProposée |
P8834
|
FINISHED |
| Object | marché artisanal |
—
|
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: marché artisanal | Statement: [Lumières de Noël de Montbéliard, activitéProposée, marché artisanal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activitéProposée Context triple: [Lumières de Noël de Montbéliard, activitéProposée, marché artisanal]
-
A.
activity
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
B.
activityType
chosen
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
C.
otherActivity
Indicates that an entity is engaged in an activity that is different from a primary, specified, or expected activity.
-
D.
activityRequires
Indicates that the performance or initiation of one activity depends on the prior availability, completion, or presence of another specified activity or condition.
-
E.
settingOfActivities
Indicates that a particular place or context serves as the environment in which certain activities occur or are carried out.
- 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_69f76e5115588190ad8738860b7bc68b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: May 3, 2026, 4:10 p.m.