Triple
T17407577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hohlenstein-Stadel cave |
E423258
|
entity |
| Predicate | hasFindType |
P25771
|
FINISHED |
| Object | figurative sculpture |
—
|
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: figurative sculpture | Statement: [Hohlenstein-Stadel cave, hasFindType, figurative sculpture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFindType Context triple: [Hohlenstein-Stadel cave, hasFindType, figurative sculpture]
-
A.
hasDiscoveryType
Indicates the specific manner, method, or category by which something was discovered.
-
B.
haveType
Indicates that an entity belongs to or is classified under a specified type or category.
-
C.
containsFinding
chosen
Indicates that one entity includes, encompasses, or holds a particular finding as part of its content or results.
-
D.
hasFilterType
Indicates that an entity is associated with, or constrained by, a specific type or category of filter applied to it.
-
E.
hasLoadType
Indicates the type or category of load associated with an entity (e.g., electrical, mechanical, data, or other load classifications).
- 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43b08d5a881909e7a5b2ae2c60898 |
completed | April 19, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69e3b02e6cc88190986e85e64ce9383e |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:46 a.m.