Triple
T14689203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | known world (A Song of Ice and Fire) |
E344995
|
entity |
| Predicate | hasFeature |
P182
|
FINISHED |
| Object | Wall |
E960512
|
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: Wall | Statement: [known world (A Song of Ice and Fire), hasFeature, Wall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wall Context triple: [known world (A Song of Ice and Fire), hasFeature, Wall]
-
A.
Wall
Wall is a village in Northumberland, England, known for its proximity to Hadrian’s Wall and its historic rural character.
-
B.
Wall
Wall is a common English surname borne by various notable individuals across sports, politics, and the arts.
-
C.
Parede
Parede is a coastal town and civil parish in the municipality of Cascais, Portugal, known for its beaches and residential character within the Lisbon metropolitan area.
-
D.
the Wall
chosen
The Wall is a colossal ice fortification in the far north of Westeros that serves as a barrier against the dangers beyond in the world of "A Song of Ice and Fire" and "Game of Thrones."
-
E.
Walls
Walls is a well-known ice cream brand in Unilever’s global frozen desserts portfolio, recognized for its wide range of frozen treats sold under various local names worldwide.
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb5844de481908a796eaa474bfde9 |
completed | April 14, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde189771c81909289b8b044e32547 |
completed | May 8, 2026, 1:13 p.m. |
Created at: April 10, 2026, 1:28 a.m.