Triple
T38387859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cloches à travers les feuilles |
E899626
|
entity |
| Predicate | workNumberInImagesII |
P190825
|
FINISHED |
| Object | 1 |
—
|
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: 1 | Statement: [Cloches à travers les feuilles, workNumberInImagesII, 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workNumberInImagesII Context triple: [Cloches à travers les feuilles, workNumberInImagesII, 1]
-
A.
appearsInWorkNumber
Indicates that an entity is featured or occurs within a specific numbered work in a series or collection.
-
B.
worksNumber
Indicates that an entity is identified or referenced by a specific works number, typically denoting a particular work, item, or production instance.
-
C.
workNumberInSet
Indicates that a particular work number belongs to, or is included within, a specified set of work numbers.
-
D.
workNumberInOpus8
Indicates that a work is assigned a specific number within Opus 8 of a composer’s catalog.
-
E.
workNumberInBookI
Indicates that a specific work is assigned a particular sequence number within the first book of a collection or series.
- 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_69f76e5c9b808190b486523f5c2f817d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
| PDg | Predicate description generation | batch_69fcd148e6d4819082c118832ecc599b |
completed | May 7, 2026, 5:52 p.m. |
Created at: May 3, 2026, 4:31 p.m.