Triple
T3015079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pembroke Castle |
E82317
|
entity |
| Predicate | partiallyDemolishedInPeriod |
P28166
|
FINISHED |
| Object | mid-17th century |
—
|
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: mid-17th century | Statement: [Pembroke Castle, partiallyDemolishedInPeriod, mid-17th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partiallyDemolishedInPeriod Context triple: [Pembroke Castle, partiallyDemolishedInPeriod, mid-17th century]
-
A.
partiallyDemolishedInCentury
chosen
Indicates that an entity was only partly demolished during a specified century, rather than being completely destroyed.
-
B.
demolitionYearApprox
Indicates that an entity was demolished in or around a particular year, where the year is an approximate rather than an exact value.
-
C.
demolitionPeriod
Indicates the time span during which the demolition of an entity or structure takes place.
-
D.
demolishedWith
Indicates that one entity was destroyed or torn down using another specified tool, method, or agent.
-
E.
hasDemolitionOrDestruction
Indicates that one entity causes, undergoes, or is associated with the demolition or destruction of 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_69ad8b1eb53481908c39bbcd1ec104b2 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a6b37288190a6965d183ca4b08b |
completed | March 8, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69ad961a97188190809dc73430a8eda8 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.