Triple
T11705717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donnington Castle |
E278230
|
entity |
| Predicate | battlementFeature |
P101353
|
FINISHED |
| Object | turreted gatehouse |
—
|
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: turreted gatehouse | Statement: [Donnington Castle, battlementFeature, turreted gatehouse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: battlementFeature Context triple: [Donnington Castle, battlementFeature, turreted gatehouse]
-
A.
fortifiedBuilding
Indicates that a building is strengthened or reinforced for defense against attacks or intrusions.
-
B.
castleBuilt
Indicates that a castle has been constructed or established, typically by a specific agent or during a particular time period.
-
C.
castleOverlooks
Indicates that a castle is positioned so that it has a clear, elevated view over a particular area, object, or landscape.
-
D.
eraOfFortification
Indicates the historical time period during which a structure or site was fortified or equipped with defensive works.
-
E.
castleBuiltOf
Indicates that a castle is constructed primarily from a specified material.
- 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_69d6aaff2ce88190b4a1e4b341ad5377 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a49c8c38819083d83f5fdec52b7f |
completed | April 10, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69d88a7b30948190b616a9db5c5488d5 |
completed | April 10, 2026, 5:28 a.m. |
| PDg | Predicate description generation | batch_69d89546a8688190b51455b5e12caf91 |
completed | April 10, 2026, 6:14 a.m. |
Created at: April 8, 2026, 9:40 p.m.