Triple
T34745238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bonkyll, Berwickshire |
E1001617
|
entity |
| Predicate | hasFormerStructure |
P196100
|
FINISHED |
| Object | Bonkyll Castle |
—
|
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: Bonkyll Castle | Statement: [Bonkyll, Berwickshire, hasFormerStructure, Bonkyll Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFormerStructure Context triple: [Bonkyll, Berwickshire, hasFormerStructure, Bonkyll Castle]
-
A.
hasFormerEntity
Indicates that one entity previously existed in a different form, role, or identity that is represented by another entity.
-
B.
hasFormerType
Indicates that an entity previously had a certain type or classification that has since changed.
-
C.
hasStructureHistory
Indicates that there exists a record or account detailing the past states, changes, or development of a structure over time.
-
D.
hasFormerParent
Indicates that an entity was previously the parent of another entity but no longer holds that parental role or status.
-
E.
hasFormerCode
Indicates that an entity was previously identified or referenced by an earlier code that is no longer current.
- 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_69f76db0367081909b57c50a7fb03025 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fe066d62b48190867df334039be786 |
completed | May 8, 2026, 3:51 p.m. |
| PD | Predicate disambiguation | batch_69fe03afde3c8190a5b9b0778d19eb1a |
completed | May 8, 2026, 3:39 p.m. |
| PDg | Predicate description generation | batch_69fe066b623c819085205fbea901e3cf |
completed | May 8, 2026, 3:51 p.m. |
Created at: May 3, 2026, 3:59 p.m.