Triple
T37870967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Villa Romana del Casale |
E944602
|
entity |
| Predicate | notableMosaic |
P104069
|
FINISHED |
| Object | bikini girls mosaic |
E441555
|
NE 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: bikini girls mosaic | Statement: [Villa Romana del Casale, notableMosaic, bikini girls mosaic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableMosaic Context triple: [Villa Romana del Casale, notableMosaic, bikini girls mosaic]
-
A.
notableMural
Indicates that an entity is a mural distinguished by particular significance, prominence, or recognition.
-
B.
notableDecoration
Indicates that an entity has received a particular honor, award, or decoration that is considered especially significant or distinguished.
-
C.
notableBoard
Indicates that an entity serves on, or is significantly associated with, a board that is notable or of particular importance.
-
D.
notableMap
Indicates that there is a map which is especially significant, well-known, or noteworthy in relation to the subject.
-
E.
notableArtObject
chosen
Indicates a relationship where an entity is recognized as an art object of particular significance, prominence, or cultural importance in connection to another entity.
- F. None of above.
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_69f76eef55d481908ca6660b4b532550 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a410426df208190a8c5f2a14f4e9935 |
completed | June 28, 2026, 11:23 a.m. |
| PD | Predicate disambiguation | batch_6a037a192a008190a9917688a9e804f4 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:19 p.m.