Triple
T4285539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isles of Scilly |
E97259
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object |
St Mary’s
St Mary’s is the largest and most populous island of the Isles of Scilly, serving as the archipelago’s main administrative and transport hub.
|
E428023
|
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: St Mary’s | Statement: [Isles of Scilly, hasIsland, St Mary’s]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: St Mary’s Context triple: [Isles of Scilly, hasIsland, St Mary’s]
-
A.
St Mary
St Mary, also known as the Virgin Mary, is a central figure in Christianity revered as the mother of Jesus Christ and honored in numerous churches and cathedrals worldwide.
-
B.
St Marys
St Marys is a small coastal village on Mainland, the largest island of Orkney in northern Scotland.
-
C.
St Mary’s Church
St Mary’s Church is a historic Christian parish church serving the community of St Neots in Cambridgeshire, England.
-
D.
St Mary Magdalene Church
St Mary Magdalene Church is a historic Christian parish church serving the village community of Pentney in Norfolk, England.
-
E.
St Mary Magdalene Church
St Mary Magdalene Church is a historic Christian church located in the seaside town of Torquay in Devon, England.
- 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: St Mary’s Triple: [Isles of Scilly, hasIsland, St Mary’s]
Generated description
St Mary’s is the largest and most populous island of the Isles of Scilly, serving as the archipelago’s main administrative and transport hub.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: St Mary’s Target entity description: St Mary’s is the largest and most populous island of the Isles of Scilly, serving as the archipelago’s main administrative and transport hub.
-
A.
St Mary
St Mary, also known as the Virgin Mary, is a central figure in Christianity revered as the mother of Jesus Christ and honored in numerous churches and cathedrals worldwide.
-
B.
St Marys
St Marys is a small coastal village on Mainland, the largest island of Orkney in northern Scotland.
-
C.
St Mary’s Church
St Mary’s Church is a historic Christian parish church serving the community of St Neots in Cambridgeshire, England.
-
D.
St Mary Magdalene Church
St Mary Magdalene Church is a notable 19th-century Anglican church in the Paddington area of London, recognized for its rich Gothic Revival architecture and ornate interior decoration.
-
E.
St Mary Magdalene Church
St Mary Magdalene Church is a historic Christian church located in the seaside town of Torquay in Devon, England.
- 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_69b3454595848190a0e6bbb6a2bea040 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3505bff588190919a4ef547f607c2 |
completed | March 12, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5c72804ac81908f8d2c111276b6b7 |
completed | March 14, 2026, 8:38 p.m. |
| NEDg | Description generation | batch_69b5c7ab41fc81909813233bd729e989 |
completed | March 14, 2026, 8:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5c81d6e188190a1f0f21a990943d0 |
completed | March 14, 2026, 8:42 p.m. |
Created at: March 12, 2026, 11:07 p.m.