Triple
T17179664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arundel Castle |
E416947
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Arundel |
E140085
|
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: Arundel | Statement: [Arundel Castle, locatedIn, Arundel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arundel Context triple: [Arundel Castle, locatedIn, Arundel]
-
A.
Arundel
chosen
Arundel is a historic market town in southern England, renowned for its medieval castle and cathedral overlooking the River Arun.
-
B.
Thrupp
Thrupp is a small canal-side village in Oxfordshire, England, known for its historic wharf and picturesque setting along the Oxford Canal.
-
C.
Arundell
Arundell is an English noble family name historically associated with prominent aristocratic lineages, particularly in Cornwall and surrounding regions.
-
D.
Dunstable
Dunstable is a historic market town in Bedfordshire, England, known for its location at the crossroads of ancient routes and its proximity to the Chiltern Hills.
-
E.
Willingdon
Willingdon is a village in East Sussex, England, situated near the town of Hailsham.
- 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_69d886d5f34c8190b24564dfaa63f3fb |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3fc10afb48190a71f4a46f0280a14 |
completed | April 18, 2026, 9:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fca04cc8190a9df230078fbe268 |
completed | May 11, 2026, 4:49 a.m. |
Created at: April 10, 2026, 5:37 a.m.