Triple
T12714333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cowgate |
E303797
|
entity |
| Predicate | connectedTo |
P37
|
FINISHED |
| Object | Grassmarket |
E150660
|
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: Grassmarket | Statement: [Cowgate, connectedTo, Grassmarket]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grassmarket Context triple: [Cowgate, connectedTo, Grassmarket]
-
A.
Grassmarket
chosen
Grassmarket is a historic marketplace and lively square in Edinburgh’s Old Town, known for its pubs, restaurants, and views up to Edinburgh Castle.
-
B.
St Andrew Square
St Andrew Square is a central public square and major transport hub in Edinburgh, Scotland, surrounded by offices, shops, and historic buildings.
-
C.
Sauchiehall Street
Sauchiehall Street is one of Glasgow’s main city-centre thoroughfares, known for its shops, bars, and cultural venues.
-
D.
Christie Street
Christie Street is a north–south street in Toronto, Ontario, running through several downtown neighbourhoods including the western edge of Koreatown.
-
E.
St James’s Street
St James’s Street is a historic thoroughfare in central London’s St James’s district, known for its gentlemen’s clubs, traditional shops, and proximity to royal and political institutions.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9620a7554819083784897ff690652 |
completed | April 10, 2026, 8:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f671bad5108190915d14c3ec3d2e27 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:23 p.m.