Triple
T15410205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doran Martell |
E368567
|
entity |
| Predicate | seat |
P75
|
FINISHED |
| Object | Sunspear |
E345003
|
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: Sunspear | Statement: [Doran Martell, seat, Sunspear]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sunspear Context triple: [Doran Martell, seat, Sunspear]
-
A.
Sunspear
chosen
Sunspear is the coastal desert stronghold and capital of Dorne, serving as the ancestral seat of House Martell in the world of Westeros.
-
B.
Sorauren
Sorauren is a village in northern Spain, near Pamplona in Navarre, known as a historic battlefield site from the Peninsular War.
-
C.
Nelion
Nelion is one of the main twin summits of Mount Kenya, renowned among climbers for its challenging rock routes and high-altitude alpine terrain.
-
D.
Rodalquilar
Rodalquilar is a small former mining village in Spain’s Almería province, known for its volcanic landscapes, abandoned gold mines, and beaches within the Cabo de Gata-Níjar Natural Park.
-
E.
Shandar
Shandar was a French avant-garde record label known for releasing experimental and free jazz recordings in the 1970s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85a16c68c819099c1b547fbc87b32 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03ea4f13c819085d26fd32b5dca6f |
completed | April 16, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1a7356548190af5651ab0bc03ab9 |
completed | May 9, 2026, 11:28 a.m. |
Created at: April 10, 2026, 3:20 a.m.