Triple
T17132760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bonnanaro culture |
E415761
|
entity |
| Predicate | hasMainTypeOfArtifact |
P40733
|
FINISHED |
| Object | handmade pottery |
—
|
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: handmade pottery | Statement: [Bonnanaro culture, hasMainTypeOfArtifact, handmade pottery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainTypeOfArtifact Context triple: [Bonnanaro culture, hasMainTypeOfArtifact, handmade pottery]
-
A.
hasTypeOfArtifact
chosen
Indicates that one entity is classified as, or belongs to, a particular type or category of artifact in relation to another entity.
-
B.
hasMainArch
Indicates that an entity possesses or features a primary or central arch structure.
-
C.
hasSignificantArtifact
Indicates that an entity possesses or is associated with an artifact that is of notable importance, influence, or relevance within a given context.
-
D.
hasMainKeepType
Indicates the specific type or category of main keep associated with a structure or site.
-
E.
hasMajorType
Indicates that an entity belongs to or is categorized under a primary or overarching type or classification.
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f02ba4cc8190b6f433e08e958d83 |
completed | April 18, 2026, 8:57 p.m. |
| PD | Predicate disambiguation | batch_69e3830192ac819091344a9e5a36c8c9 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:36 a.m.