Triple
T14484993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beric Dondarrion |
E359203
|
entity |
| Predicate | origin |
P410
|
FINISHED |
| Object |
Blackhaven
Blackhaven is a castle and the seat of House Dondarrion in the stormlands of Westeros in the world of A Song of Ice and Fire.
|
E1101055
|
NE FINISHED |
How this triple was built (4 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: Blackhaven | Statement: [Beric Dondarrion, origin, Blackhaven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blackhaven Context triple: [Beric Dondarrion, origin, Blackhaven]
-
A.
Welhaven
Welhaven is a Norwegian surname most notably associated with the 19th-century poet and critic Johan Sebastian Welhaven.
-
B.
Harlem Désir
Harlem Désir is a French politician and former Member of the European Parliament who has held prominent roles in the Socialist Party and later served as a diplomat focused on European and human rights issues.
-
C.
Southside
"Southside" is a hip-hop track by Common featuring Kanye West, known for its soulful production and reflective lyrics.
-
D.
Southside
Southside is a shopping and leisure centre located on Victoria Street in central London.
-
E.
Southside
Southside is a central district in Birmingham, England, known for its entertainment venues, nightlife, and the city’s Chinese Quarter and Gay Village.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Blackhaven Triple: [Beric Dondarrion, origin, Blackhaven]
Generated description
Blackhaven is a castle and the seat of House Dondarrion in the stormlands of Westeros in the world of A Song of Ice and Fire.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Blackhaven Target entity description: Blackhaven is a castle and the seat of House Dondarrion in the stormlands of Westeros in the world of A Song of Ice and Fire.
-
A.
Welhaven
Welhaven is a Norwegian surname most notably associated with the 19th-century poet and critic Johan Sebastian Welhaven.
-
B.
Harlem Désir
Harlem Désir is a French politician and former Member of the European Parliament who has held prominent roles in the Socialist Party and later served as a diplomat focused on European and human rights issues.
-
C.
Southside
"Southside" is a hip-hop track by Common featuring Kanye West, known for its soulful production and reflective lyrics.
-
D.
Southside
Southside is a central district in Birmingham, England, known for its entertainment venues, nightlife, and the city’s Chinese Quarter and Gay Village.
-
E.
Southside
Southside is an American record producer and rapper best known for his hard-hitting trap beats and work with artists like Future, Waka Flocka Flame, and Gucci Mane.
- F. None of above. chosen
Provenance (5 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924d7f4c8190b1f62b5ffe1ff649 |
completed | April 14, 2026, 7:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd64a73cf48190811d6de182e891c4 |
completed | May 8, 2026, 4:20 a.m. |
| NEDg | Description generation | batch_69fd66d3f2448190b8926c479ce95e83 |
completed | May 8, 2026, 4:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd67b5cd2c8190871d22ebdc64dd11 |
completed | May 8, 2026, 4:33 a.m. |
Created at: April 10, 2026, 1:20 a.m.