Triple
T4024371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Etruscan Dressing Room at Osterley Park |
E91354
|
entity |
| Predicate | hasWallPainting |
P23612
|
FINISHED |
| Object | Etruscan-style panels |
—
|
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: Etruscan-style panels | Statement: [Etruscan Dressing Room at Osterley Park, hasWallPainting, Etruscan-style panels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWallPainting Context triple: [Etruscan Dressing Room at Osterley Park, hasWallPainting, Etruscan-style panels]
-
A.
paintedEvery
Indicates that an entity applied paint to each and every relevant item in a specified set or domain.
-
B.
hasArtInstallation
Indicates that an entity features or contains an art installation as part of its space or composition.
-
C.
hasFrescoes
chosen
Indicates that something contains or is adorned with fresco paintings as part of its structure or decoration.
-
D.
hasWallTileColor
Indicates that an entity’s wall tiles possess a specific color.
-
E.
hasCarvings
Indicates that one entity features or contains carved designs or engravings on its surface, created by another entity or process.
- 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_69aed9618b04819081750d979d2af098 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefacfb23081909a46878adb90ea6c |
completed | March 9, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69aef8fc78ec819092d4dab88d85a141 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:35 p.m.