Triple
T8686151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Thermae of Odessos |
E206163
|
entity |
| Predicate | floorHeatingSystem |
P34898
|
FINISHED |
| Object | hypocaust |
—
|
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: hypocaust | Statement: [Roman Thermae of Odessos, floorHeatingSystem, hypocaust]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floorHeatingSystem Context triple: [Roman Thermae of Odessos, floorHeatingSystem, hypocaust]
-
A.
hasHeating
chosen
Indicates that an entity is equipped with or provides a heating system or heating capability.
-
B.
floorType
Indicates the type or material classification of a floor associated with an entity.
-
C.
floorConfiguration
Indicates how the layout, structure, or arrangement of floors or levels is organized or configured in relation to one another.
-
D.
floor
Indicates that one entity is located on or forms the walking surface (the floor) beneath another entity within a space.
-
E.
hasFlooring
Indicates that one entity is equipped with or covered by a particular type of flooring material provided by another entity.
- 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_69ca835379688190aa06b9d98e684d58 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4aec1f8c8190a9ab1a73c2dbcd3c |
completed | March 31, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69cc4569f9048190b9c86b4c81103d35 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:33 p.m.