Triple
T664524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tulle |
E12829
|
entity |
| Predicate | twinnedWith |
P1072
|
FINISHED |
| Object |
Ludlow
Ludlow is a historic market town in Shropshire, England, renowned for its well-preserved medieval architecture, Norman castle, and vibrant food culture.
|
E82172
|
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: Ludlow | Statement: [Tulle, twinnedWith, Ludlow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ludlow Context triple: [Tulle, twinnedWith, Ludlow]
-
A.
Castleton
Castleton is a picturesque village in England’s Peak District, known for its surrounding hills, show caves, and historic Peveril Castle.
-
B.
Milltown
Milltown is a small hamlet within the Town of Southeast in Putnam County, New York.
-
C.
Ward Hill
Ward Hill is a prominent hill on the Orkney island of Hoy in Scotland, known for its sweeping views and rugged, heather-covered slopes.
-
D.
Mon Valley Works
Mon Valley Works is a large integrated steel production complex in Pennsylvania operated by United States Steel that manufactures a range of steel products for industrial and commercial use.
-
E.
Winchester
Winchester is a suburban town in Middlesex County, Massachusetts, known for its residential character and proximity to Boston.
- 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: Ludlow Triple: [Tulle, twinnedWith, Ludlow]
Generated description
Ludlow is a historic market town in Shropshire, England, renowned for its well-preserved medieval architecture, Norman castle, and vibrant food culture.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ludlow Target entity description: Ludlow is a historic market town in Shropshire, England, renowned for its well-preserved medieval architecture, Norman castle, and vibrant food culture.
-
A.
Castleton
Castleton is a picturesque village in England’s Peak District, known for its surrounding hills, show caves, and historic Peveril Castle.
-
B.
Milltown
Milltown is a small hamlet within the Town of Southeast in Putnam County, New York.
-
C.
Ward Hill
Ward Hill is a prominent hill on the Orkney island of Hoy in Scotland, known for its sweeping views and rugged, heather-covered slopes.
-
D.
Mon Valley Works
Mon Valley Works is a large integrated steel production complex in Pennsylvania operated by United States Steel that manufactures a range of steel products for industrial and commercial use.
-
E.
Winchester
Winchester is a historic cathedral city in Hampshire, England, known for its medieval architecture and former status as the capital of the Kingdom of Wessex.
- 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_69a493355dec819098d4244b2fa34885 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49fd3d8fc8190866af5c76c08f486 |
completed | March 1, 2026, 8:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a5c39abcbc819093797700dc32d25a |
completed | March 2, 2026, 5:06 p.m. |
| NEDg | Description generation | batch_69a5c564d368819082b877f43236d949 |
completed | March 2, 2026, 5:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a5cca1851c81908e57e75dc217e517 |
completed | March 2, 2026, 5:45 p.m. |
Created at: March 1, 2026, 7:36 p.m.