Triple
T8574797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dundas |
E203020
|
entity |
| Predicate | associatedEstate |
P347
|
FINISHED |
| Object |
Arniston
Arniston is a historic Scottish country estate in Midlothian, long associated with the influential Dundas family.
|
E742594
|
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: Arniston | Statement: [Dundas, associatedEstate, Arniston]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arniston Context triple: [Dundas, associatedEstate, Arniston]
-
A.
Ashton
Ashton is a small village in the town of Cumberland in Providence County, Rhode Island, known for its historic mill district along the Blackstone River.
-
B.
Ashton
Ashton is a masculine given name of English origin that has become well known through figures such as actor and entrepreneur Ashton Kutcher.
-
C.
Ashton
Ashton is a small town in South Africa’s Western Cape, known for its fruit farming and position along the scenic Route 62.
-
D.
Ashton
Ashton is a small coastal town on Union Island in Saint Vincent and the Grenadines, known as one of the island’s main settlements.
-
E.
Shandon
Shandon is a small rural community in California’s Central Coast region known for its agriculture and proximity to local vineyards and ranchlands.
- 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: Arniston Triple: [Dundas, associatedEstate, Arniston]
Generated description
Arniston is a historic Scottish country estate in Midlothian, long associated with the influential Dundas family.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Arniston Target entity description: Arniston is a historic Scottish country estate in Midlothian, long associated with the influential Dundas family.
-
A.
Ashton
Ashton is a masculine given name of English origin that has become well known through figures such as actor and entrepreneur Ashton Kutcher.
-
B.
Ashton
Ashton is a small village in the town of Cumberland in Providence County, Rhode Island, known for its historic mill district along the Blackstone River.
-
C.
Ashton
Ashton is a small town in South Africa’s Western Cape, known for its fruit farming and position along the scenic Route 62.
-
D.
Ashton
Ashton is a small coastal town on Union Island in Saint Vincent and the Grenadines, known as one of the island’s main settlements.
-
E.
Shandon
Shandon is a small rural community in California’s Central Coast region known for its agriculture and proximity to local vineyards and ranchlands.
- 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_69ca8328ebe481909a8c038fa79959b4 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbea947f188190af469babaa73ddf6 |
completed | March 31, 2026, 3:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce8995d1d081909f6a27220c2c267e |
completed | April 2, 2026, 3:21 p.m. |
| NEDg | Description generation | batch_69ce8a9df47c81909ba9ef8dff1db7b1 |
completed | April 2, 2026, 3:26 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce8b48841c8190bcf11aeb25355649 |
completed | April 2, 2026, 3:29 p.m. |
Created at: March 30, 2026, 6:21 p.m.