Triple
T3387697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jedburgh Abbey |
E71341
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Jedburgh |
E154658
|
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: Jedburgh | Statement: [Jedburgh Abbey, locatedIn, Jedburgh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jedburgh Context triple: [Jedburgh Abbey, locatedIn, Jedburgh]
-
A.
Jedburgh
chosen
Jedburgh is a historic town in the Scottish Borders, known for its medieval abbey, ruined castle jail, and role as a former royal burgh near the English border.
-
B.
Dunkeld
Dunkeld is a historic town in Perth and Kinross, Scotland, known for its picturesque setting on the River Tay and its medieval cathedral.
-
C.
Linlithgow
Linlithgow is a historic Scottish town in West Lothian, best known for the ruins of Linlithgow Palace, birthplace of Mary, Queen of Scots.
-
D.
Hawick
Hawick is a historic textile-producing town in the Scottish Borders, known for its knitwear industry and rugby tradition.
-
E.
Haddington
Haddington is a residential neighborhood in the western section of Philadelphia, Pennsylvania, known for its rowhouses and diverse urban 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_69ad85a8fd9c819095ecedf838d2bf1b |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb66448fc8190a8582145f02bb1d9 |
completed | March 8, 2026, 5:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b33458130881908a2b47abd91f4ea8 |
completed | March 12, 2026, 9:47 p.m. |
Created at: March 8, 2026, 3:14 p.m.