Triple
T17407604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geißenklösterle |
E423259
|
entity |
| Predicate | artifactsDatedTo |
P127348
|
FINISHED |
| Object | more than 40,000 years ago |
—
|
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: more than 40,000 years ago | Statement: [Geißenklösterle, artifactsDatedTo, more than 40,000 years ago]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: artifactsDatedTo Context triple: [Geißenklösterle, artifactsDatedTo, more than 40,000 years ago]
-
A.
approximateDepictionDate
Indicates the estimated or inferred date when a depiction was created, rather than a precise, confirmed date.
-
B.
yearOfCreationEnd
Indicates the year in which the creation or production of something was completed or came to an end.
-
C.
estimatedYearOfCreation
Indicates the year in which something is believed or approximated to have been created, rather than a precisely known creation year.
-
D.
earliestPaintingsDateTo
Indicates the earliest known date or time period to which certain paintings can be traced or assigned.
-
E.
earliestFabricDate
Indicates the earliest date at which the fabric (or material) associated with an entity was created or first produced.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69e3b2a33e8481908fa6ef45290d08aa |
completed | April 18, 2026, 4:34 p.m. |
Created at: April 10, 2026, 5:46 a.m.