Triple

T18045868
Position Surface form Disambiguated ID Type / Status
Subject St Martin’s E431771 entity
Predicate hasSettlement P1068 FINISHED
Object Lower Town
Lower Town is a small settlement associated with St Martin’s in the Isles of Scilly, England.
E1302294 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: Lower Town | Statement: [St Martin’s, hasSettlement, Lower Town]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lower Town
Context triple: [St Martin’s, hasSettlement, Lower Town]
  • A. Lower Town
    Lower Town is the riverside section of Belgrade Fortress, historically serving as its commercial and military quarter along the confluence of the Sava and Danube rivers.
  • B. Lower Town
    Lower Town is a district within Oranjestad, the capital city of Aruba, known for its coastal setting and local residential character.
  • C. Lower Town
    Lower Town is one of Ottawa’s oldest central neighborhoods, known for its historic character, diverse communities, and proximity to major federal landmarks and the ByWard Market.
  • D. Lower Town
    Lower Town is the historic lower district of Sibiu, Romania, known for its medieval streets, craftsmen’s houses, and well-preserved fortifications.
  • E. Lower Town
    Lower Town is the seaside medieval quarter of Monemvasia, known for its preserved stone houses, narrow streets, and historic churches beneath the fortress above.
  • 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: Lower Town
Triple: [St Martin’s, hasSettlement, Lower Town]
Generated description
Lower Town is a small settlement associated with St Martin’s in the Isles of Scilly, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lower Town
Target entity description: Lower Town is a small settlement associated with St Martin’s in the Isles of Scilly, England.
  • A. Lower Town
    Lower Town is the riverside section of Belgrade Fortress, historically serving as its commercial and military quarter along the confluence of the Sava and Danube rivers.
  • B. Lower Town
    Lower Town is a district within Oranjestad, the capital city of Aruba, known for its coastal setting and local residential character.
  • C. Lower Town
    Lower Town is one of Ottawa’s oldest central neighborhoods, known for its historic character, diverse communities, and proximity to major federal landmarks and the ByWard Market.
  • D. Lower Town
    Lower Town is the historic lower district of Sibiu, Romania, known for its medieval streets, craftsmen’s houses, and well-preserved fortifications.
  • E. Lower Town
    Lower Town is the seaside medieval quarter of Monemvasia, known for its preserved stone houses, narrow streets, and historic churches beneath the fortress above.
  • 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_69d8b906482481908183315b9ecf9994 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4bff202088190ae971879348e2294 completed April 19, 2026, 11:43 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0349bb99508190ba6b1f8e4ac2b599 completed May 12, 2026, 3:39 p.m.
NEDg Description generation batch_6a034b4fd4fc8190bd75aa51a8f3d2d4 completed May 12, 2026, 3:46 p.m.
NED2 Entity disambiguation (via description) batch_6a034bc081d08190aa29065fdaecc5b2 completed May 12, 2026, 3:48 p.m.
Created at: April 10, 2026, 10:25 a.m.