Triple
T16969345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Close (Salisbury) |
E411624
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Arundells |
E411641
|
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: Arundells | Statement: [The Close (Salisbury), contains, Arundells]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arundells Context triple: [The Close (Salisbury), contains, Arundells]
-
A.
Arundells
chosen
Arundells is a historic house and former home of British Prime Minister Sir Edward Heath, located within the Cathedral Close in Salisbury, England.
-
B.
Arundell
Arundell is an English noble family name historically associated with prominent aristocratic lineages, particularly in Cornwall and surrounding regions.
-
C.
Radclyffe
Radclyffe is an English surname historically associated with the noble Radclyffe family, including the Earls of Derwentwater.
-
D.
Arundel
Arundel is a historic market town in southern England, renowned for its medieval castle and cathedral overlooking the River Arun.
-
E.
Arundel Mills
Arundel Mills is a large outlet and retail shopping mall and entertainment complex located in Hanover, Maryland.
- 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_69d886c9c9d481909afe222093641cae |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d0a86c64819092831f8ddf1e536b |
completed | April 18, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d471d4248190acf40b6c11926a65 |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:31 a.m.