Triple
T37929819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medusa head mosaic |
E946183
|
entity |
| Predicate | partOfRoomType |
P139229
|
FINISHED |
| Object | reception room |
—
|
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: reception room | Statement: [Medusa head mosaic, partOfRoomType, reception room]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfRoomType Context triple: [Medusa head mosaic, partOfRoomType, reception room]
-
A.
roomSettingOfPart
Indicates that a room or environmental setting is the contextual location or configuration associated with a specific part or component.
-
B.
partOfFacility
Indicates that one entity is a component, section, or sub-unit belonging to a larger facility.
-
C.
chamberType
Indicates the specific kind or category of chamber associated with an entity (e.g., room, compartment, or enclosed space type).
-
D.
typeOfChamber
Indicates the specific kind or category of chamber that an entity belongs to or is classified as.
-
E.
usedInRoom
chosen
Indicates that something is utilized or functions within a particular room or enclosed space.
- 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_69f76ef3b7248190892fb9706423be7c |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a019579463c8190b51e39183b57bbaf |
completed | May 11, 2026, 8:38 a.m. |
| PD | Predicate disambiguation | batch_6a0192d309488190a3d86c93e7138c77 |
completed | May 11, 2026, 8:26 a.m. |
Created at: May 3, 2026, 4:20 p.m.