Triple
T3015067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pembroke Castle |
E82317
|
entity |
| Predicate | rebuiltInStone |
P45011
|
FINISHED |
| Object | 12th 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: 12th century | Statement: [Pembroke Castle, rebuiltInStone, 12th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rebuiltInStone Context triple: [Pembroke Castle, rebuiltInStone, 12th century]
-
A.
rebuiltFor
Indicates that one entity has been reconstructed, renovated, or modified specifically to serve the needs, purposes, or use of another entity.
-
B.
rebuiltUnder
Indicates that an entity was reconstructed or restored while being subject to the authority, control, or governance of another entity.
-
C.
rebuiltAsPalace
Indicates that a structure or building was reconstructed or transformed into a palace.
-
D.
rebuiltInStyle
Indicates that something has been reconstructed or renovated following the characteristics, design principles, or aesthetic conventions of a specified style.
-
E.
rebuild
Indicates restoring or constructing again something that was previously built, often after damage, destruction, or significant alteration.
- 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_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. |
| PDg | Predicate description generation | batch_69ad97ba55dc8190b6dddddfb751cf64 |
completed | March 8, 2026, 3:37 p.m. |
Created at: March 8, 2026, 3 p.m.