Triple
T25119591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isthmo-Colombian societies |
E629229
|
entity |
| Predicate | producedArtifactType |
P162081
|
FINISHED |
| Object | stone spheres |
—
|
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: stone spheres | Statement: [Isthmo-Colombian societies, producedArtifactType, stone spheres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: producedArtifactType Context triple: [Isthmo-Colombian societies, producedArtifactType, stone spheres]
-
A.
producedArtifactType
chosen
Indicates the type or category of artifact that is created or generated as the result of a production process or activity.
-
B.
componentTypeProduced
Indicates that one entity produces or manufactures a specific type of component as an output of its activity or process.
-
C.
producedContentType
Indicates that an entity has created or generated content of a specified type or format.
-
D.
producedModel
Indicates that one entity created, manufactured, or generated the other entity as a model or product.
-
E.
producedAs
Indicates that one entity is created, generated, or brought into existence as a result or output of another entity or process.
- 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_69e2ff3288048190bd82c3b7f7bd0e62 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f62d89b89c8190afb372a8172111e7 |
completed | May 2, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69f62c1379f08190836c3e02b0c892df |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 18, 2026, 6:27 a.m.