Triple
T9957086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tusculum |
E195470
|
entity |
| Predicate | hadTypeOfBuilding |
P1844
|
FINISHED |
| Object | Roman theatre |
—
|
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: Roman theatre | Statement: [Tusculum, hadTypeOfBuilding, Roman theatre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadTypeOfBuilding Context triple: [Tusculum, hadTypeOfBuilding, Roman theatre]
-
A.
buildingType
chosen
Indicates the specific category or function that characterizes what kind of building something is.
-
B.
originalBuildingType
Indicates the type or category of building that something was initially constructed or designated to be, before any later changes or repurposing.
-
C.
containsBuildingType
Indicates that a location or area includes at least one building of the specified type.
-
D.
architectureType
Indicates the specific style or category of architecture that characterizes or defines an entity.
-
E.
hasBuildingHeightType
Indicates the classification or type used to characterize the height of a building in the relationship.
- 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_69ca82eaaa008190a54fa1a9f954b9ad |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb6cceb608190ad4424afaddcabfa |
completed | April 2, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9ae19c819099fb3635e57c79be |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:46 p.m.