Triple
T390440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Leith |
E8867
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object |
Granton
Granton is a coastal district in the north of Edinburgh, Scotland, historically associated with its harbour and maritime industry.
|
E55248
|
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: Granton | Statement: [Port of Leith, near, Granton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Granton Context triple: [Port of Leith, near, Granton]
-
A.
Standish
Standish is a village in Lancashire, England, known for its historic parish church and traditional English character.
-
B.
Culross
Culross is a historic coastal village in Fife, Scotland, known for its well-preserved 16th–17th century buildings and picturesque harbour.
-
C.
Montrose
Montrose is a coastal town in eastern Scotland known for its historic harbor, sandy beach, and surrounding nature reserves.
-
D.
Kanesville
Kanesville was the mid-19th-century Mormon settlement that later became the city of Council Bluffs, Iowa.
-
E.
Twain Harte
Twain Harte is a small mountain resort town in California’s Sierra Nevada known for its pine forests, outdoor recreation, and proximity to Yosemite National Park.
- 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: Granton Triple: [Port of Leith, near, Granton]
Generated description
Granton is a coastal district in the north of Edinburgh, Scotland, historically associated with its harbour and maritime industry.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Granton Target entity description: Granton is a coastal district in the north of Edinburgh, Scotland, historically associated with its harbour and maritime industry.
-
A.
Standish
Standish is a village in Lancashire, England, known for its historic parish church and traditional English character.
-
B.
Culross
Culross is a historic coastal village in Fife, Scotland, known for its well-preserved 16th–17th century buildings and picturesque harbour.
-
C.
Montrose
Montrose is a coastal town in eastern Scotland known for its historic harbor, sandy beach, and surrounding nature reserves.
-
D.
Kanesville
Kanesville was the mid-19th-century Mormon settlement that later became the city of Council Bluffs, Iowa.
-
E.
Twain Harte
Twain Harte is a small mountain resort town in California’s Sierra Nevada known for its pine forests, outdoor recreation, and proximity to Yosemite National Park.
- 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_69a2e7f55c60819097aff65ea2ca2832 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec5d73e881909101308a583c8f13 |
completed | Feb. 28, 2026, 1:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a436664f748190b8f360b1dfc0ff3d |
completed | March 1, 2026, 12:51 p.m. |
| NEDg | Description generation | batch_69a436c6f1a0819086f8d8f12bc82e87 |
completed | March 1, 2026, 12:53 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a4379eee248190a417b81afbb403ae |
completed | March 1, 2026, 12:57 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.