Triple
T25133259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cathédrale Saint-Lazare d’Autun |
E629585
|
entity |
| Predicate | tympanumAttributedTo |
P157957
|
FINISHED |
| Object | Gislebertus |
—
|
NE NERFINISHED |
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: Gislebertus | Statement: [Cathédrale Saint-Lazare d’Autun, tympanumAttributedTo, Gislebertus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tympanumAttributedTo Context triple: [Cathédrale Saint-Lazare d’Autun, tympanumAttributedTo, Gislebertus]
-
A.
hasTympanumTheme
Indicates that a subject features a specific thematic or narrative motif depicted in its tympanum (the semi-circular or triangular decorative space above a doorway or entrance).
-
B.
hasPrincipalTimpanist
Indicates that an entity (such as an orchestra) has a specific person serving as its principal timpanist.
-
C.
isSoundProducedBy
Indicates that a particular sound is generated or emitted by a specified source or entity.
-
D.
tunedBy
Indicates that one entity has been adjusted or calibrated in its settings, parameters, or configuration by another entity.
-
E.
timbrality
Indicates the relationship between sounds or musical elements in terms of their tone color or quality, distinguishing how they differ or interact based on timbre.
- F. None of above. chosen
Provenance (4 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_69e2ff338250819096ff6c8892804389 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f465fb5eb88190bb30b07f57fe4e8d |
completed | May 1, 2026, 8:36 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
| PDg | Predicate description generation | batch_69f45300bd488190bb1d4160f5534ef6 |
completed | May 1, 2026, 7:15 a.m. |
Created at: April 18, 2026, 6:28 a.m.