Triple
T12771340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castlehill |
E305252
|
entity |
| Predicate | hasNearbyLandmark |
P2064
|
FINISHED |
| Object | Lawnmarket |
E538212
|
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: Lawnmarket | Statement: [Castlehill, hasNearbyLandmark, Lawnmarket]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lawnmarket Context triple: [Castlehill, hasNearbyLandmark, Lawnmarket]
-
A.
Lawnmarket
chosen
Lawnmarket is a historic street forming part of Edinburgh’s Royal Mile, known for its traditional tenements, shops, and proximity to Edinburgh Castle.
-
B.
Lawnmarket, Edinburgh
Lawnmarket, Edinburgh is a historic street on the Royal Mile in Scotland’s capital, known for its traditional tenements, shops, and legal and civic buildings.
-
C.
Hove Lawns
Hove Lawns is a large seafront green space in Hove, England, known for its open lawns, promenade views, and use for public events and recreation.
-
D.
Smith’s Lawn
Smith’s Lawn is a renowned polo ground located within Windsor Great Park in Berkshire, England.
-
E.
Midgham Green
Midgham Green is a small green or common area within the village of Midgham in Berkshire, England, typically serving as a local open space for the community.
- 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_69d7bdf2b43c819098ae5aa68e61ea58 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96df4b36c81909bcc913dd5e535f8 |
completed | April 10, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68eba76008190ad9df2e2a5423471 |
completed | May 2, 2026, 11:54 p.m. |
Created at: April 9, 2026, 5:28 p.m.