Triple
T2287686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caernarfon Castle |
E51430
|
entity |
| Predicate | besiegedIn |
P36192
|
FINISHED |
| Object | 1294 |
—
|
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: 1294 | Statement: [Caernarfon Castle, besiegedIn, 1294]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: besiegedIn Context triple: [Caernarfon Castle, besiegedIn, 1294]
-
A.
isSiegeOf
Indicates a relationship where one event or action constitutes the military siege of a particular place, target, or entity.
-
B.
besiegingForce
Indicates a military group that is surrounding and attacking a target location or force in an attempt to capture or subdue it.
-
C.
wasFortifiedBy
Indicates that a place or structure received defensive strengthening or fortification through the actions or resources of a specified agent or entity.
-
D.
conqueredIn
Indicates that one entity gained control over another entity or territory as a result of a specific conquest event or campaign.
-
E.
currentStronghold
Indicates that an entity currently serves as the primary base, fortress, or central stronghold for another entity.
- 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_69a88b09c644819090b503456d96bf70 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abc24868048190940512fd6449d99e |
completed | March 7, 2026, 6:14 a.m. |
| PD | Predicate disambiguation | batch_69abbdbb9e4c819085fc588626ec7c09 |
completed | March 7, 2026, 5:55 a.m. |
| PDg | Predicate description generation | batch_69abbe1ecb7081909c2c66da08a48ab7 |
completed | March 7, 2026, 5:56 a.m. |
Created at: March 4, 2026, 7:48 p.m.