Triple
T33737274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady of Dragonstone |
E864454
|
entity |
| Predicate | associatedWithStronghold |
P77480
|
FINISHED |
| Object | Dragonstone castle |
E1122065
|
NE 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: Dragonstone castle | Statement: [Lady of Dragonstone, associatedWithStronghold, Dragonstone castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithStronghold Context triple: [Lady of Dragonstone, associatedWithStronghold, Dragonstone castle]
-
A.
strongholdOf
Indicates that a location serves as a primary fortified base, center of power, or main stronghold for a particular entity.
-
B.
primaryStronghold
chosen
Indicates that one location serves as the main base, fortress, or central stronghold for an entity compared to its other sites.
-
C.
strongholdRegion
Indicates that a stronghold (fortified place or base) is located within or associated with a particular geographic region.
-
D.
strongholdRecapturedWithAidOf
Indicates that a stronghold was retaken by one party with assistance or support from another party.
-
E.
associatedWithArena
Indicates a relationship in which an entity is linked or connected to a particular arena, such as by location, use, affiliation, or operation.
- F. None of above.
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_69f3498b24b8819096a65009e521d0e1 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037e0953908190b2930b3c06a40129 |
completed | May 12, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36657332ec8190acb9b5a0d59448d1 |
completed | June 20, 2026, 10:03 a.m. |
| PD | Predicate disambiguation | batch_6a0379f6c3308190b954f7810214ceed |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:44 a.m.