Triple
T30966577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ceremonial county of Dyfed |
E788973
|
entity |
| Predicate | hasPreservedCounty |
P201830
|
FINISHED |
| Object | Pembrokeshire |
—
|
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: Pembrokeshire | Statement: [ceremonial county of Dyfed, hasPreservedCounty, Pembrokeshire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPreservedCounty Context triple: [ceremonial county of Dyfed, hasPreservedCounty, Pembrokeshire]
-
A.
hasPreservedCountyFunction
Indicates that an entity continues to perform or retain the official functions and responsibilities of a county authority.
-
B.
preservedCountyEstablished
Indicates that a county’s original establishment or founding status has been maintained or formally preserved over time.
-
C.
hasPreserved
Indicates that one entity has kept another entity intact, unchanged, or maintained in its original or functional state over time.
-
D.
hasFormerCounty
Indicates that an entity was previously part of, or administered by, a particular county in the past but no longer is.
-
E.
hasParentCounty
Indicates that a given county is administratively or geographically contained within, and subordinate to, a specified parent county.
- 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_69f224c3a6b48190951add9b7b7f0271 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a0027e4a59481909417b2531daaf480 |
completed | May 10, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_6a0026a42bc08190ad3322ce625a523a |
completed | May 10, 2026, 6:33 a.m. |
| PDg | Predicate description generation | batch_6a0027e384d08190ad92a6a21c8f84b5 |
completed | May 10, 2026, 6:38 a.m. |
Created at: April 29, 2026, 8:54 p.m.