Triple
T17562660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercredi Saint |
E427730
|
entity |
| Predicate | appartientÀTradition |
P52885
|
FINISHED |
| Object | christianisme |
—
|
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: christianisme | Statement: [Mercredi Saint, appartientÀTradition, christianisme]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appartientÀTradition Context triple: [Mercredi Saint, appartientÀTradition, christianisme]
-
A.
traditionAt
Indicates that a particular tradition is practiced, observed, or associated at a specific place or location.
-
B.
isTraditionOf
chosen
Indicates that something is a customary practice, belief, or ritual associated with or belonging to a particular group, culture, or context.
-
C.
traditionIncludes
Indicates that a particular tradition encompasses, contains, or is composed of a specified element, practice, or component.
-
D.
traditionInheritedFrom
Indicates that a tradition has been passed down or derived from an earlier source, group, or culture.
-
E.
traditionClassification
Indicates how a given item, practice, or concept is categorized within a particular tradition or system of traditions.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e456285c808190953a49e77366d8bd |
completed | April 19, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fd7d048190b54ee4c6155612a5 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.