Triple
T36672877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Italia in Miniatura |
E905465
|
entity |
| Predicate | hasModelOf |
P199402
|
FINISHED |
| Object | Colosseum |
—
|
NE NERFINISHED |
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: Colosseum | Statement: [Italia in Miniatura, hasModelOf, Colosseum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasModelOf Context triple: [Italia in Miniatura, hasModelOf, Colosseum]
-
A.
hasModelIn
chosen
Indicates that an entity is represented or instantiated as a model within a specified context, system, or container.
-
B.
hasModels
Indicates that an entity possesses, defines, or is associated with one or more models (such as conceptual, mathematical, or data models).
-
C.
hasRealModel
Indicates that an abstract, theoretical, or simplified entity is associated with a corresponding concrete or physically instantiated model in the real world.
-
D.
hadModel
Indicates that an entity possessed, used, or was associated with a particular model (e.g., a product, design, or version) at some point in time.
-
E.
isModelOf
Indicates that one entity serves as a representation or abstraction that captures the structure or behavior of 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_69f76e6f10008190aea41746aa1b186e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff70ecc1a481909571b18d56d982b8 |
completed | May 9, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69ff70322a3c8190837840ea42cd3093 |
completed | May 9, 2026, 5:34 p.m. |
Created at: May 3, 2026, 4:12 p.m.