Triple
T24246668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chillida-Leku Museum |
E603392
|
entity |
| Predicate | hasMaterialInCollection |
P1845
|
FINISHED |
| Object | steel |
—
|
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: steel | Statement: [Chillida-Leku Museum, hasMaterialInCollection, steel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMaterialInCollection Context triple: [Chillida-Leku Museum, hasMaterialInCollection, steel]
-
A.
hasMaterialResource
Indicates that an entity possesses, controls, or has access to a tangible material resource.
-
B.
hasMaterialType
chosen
Indicates that something is composed of, made from, or characterized by a specific type of material.
-
C.
hasMaterialRole
Indicates that an entity participates in an activity or context by fulfilling a specific material-related role or function.
-
D.
hasMaterialOfStones
Indicates that something is composed of or contains a particular type or set of stones as its material.
-
E.
hasMaterialOption
Indicates that an entity can be made from, or is available in, one or more alternative materials.
- 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_69e2953f631c819097cbb421046bd417 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28b85349481909c21dacd48df7b8e |
completed | April 29, 2026, 10:51 p.m. |
| PD | Predicate disambiguation | batch_69f1c450aa508190bc9d372a5f6ee47a |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:04 a.m.