Triple
T10123322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BGS GeoIndex |
E223350
|
entity |
| Predicate | offersLayerType |
P92105
|
FINISHED |
| Object | bedrock geology layers |
—
|
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: bedrock geology layers | Statement: [BGS GeoIndex, offersLayerType, bedrock geology layers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersLayerType Context triple: [BGS GeoIndex, offersLayerType, bedrock geology layers]
-
A.
offersPanelType
Indicates that an entity provides or makes available a specific type of panel as part of its offerings.
-
B.
offersPlanType
Indicates that one entity provides or makes available a specific type of plan to another entity or in a given context.
-
C.
offersObject
Indicates that a subject provides or makes available a specific object to another party as an offer.
-
D.
offersServiceType
Indicates that one entity provides or makes available a specific type or category of service to another entity or the public.
-
E.
offeringType
Indicates the category or nature of what is being offered in a transaction or interaction (e.g., product, service, or other type of offering).
- 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd2ea7fe88190acb08d292a794638 |
completed | April 2, 2026, 2:22 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba1d360819087698d04a53cc87e |
completed | April 1, 2026, 4:45 p.m. |
| PDg | Predicate description generation | batch_69cd4fed19d481909d2c7ff1114664b6 |
completed | April 1, 2026, 5:03 p.m. |
Created at: March 30, 2026, 9:05 p.m.