Triple
T31033202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheinwoodian |
E790784
|
entity |
| Predicate | lowerBoundaryTypeSection |
P112329
|
FINISHED |
| Object | Ludlow, Shropshire, England |
—
|
NE NERFINISHED |
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: Ludlow, Shropshire, England | Statement: [Sheinwoodian, lowerBoundaryTypeSection, Ludlow, Shropshire, England]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lowerBoundaryTypeSection Context triple: [Sheinwoodian, lowerBoundaryTypeSection, Ludlow, Shropshire, England]
-
A.
lowerSectionType
chosen
Indicates the specific type or category assigned to the lower section of an object, structure, or entity in a larger whole.
-
B.
lowerBoundaryLocation
Indicates the place or region where the lower or bottom boundary of something is situated.
-
C.
lowerLimit
Indicates that one value serves as the minimum or smallest allowable bound or threshold for another value or range.
-
D.
upperBoundaryType
Indicates the kind or classification of the upper boundary that limits or caps a given range, interval, or extent.
-
E.
hasLowerBoundaryDefinedBy
Indicates that one entity’s lower limit, edge, or boundary is specified or determined by another entity.
- 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_69f224c97a788190b5da1ead6038a74e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f694c3e0f881909ea3548ec8ab3eaf |
completed | May 3, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69f690f13d7481908ddfefe95df2a1c2 |
completed | May 3, 2026, 12:04 a.m. |
Created at: April 29, 2026, 8:59 p.m.