Triple

T23039694
Position Surface form Disambiguated ID Type / Status
Subject Mainland, Shetland E573699 entity
Predicate hasRoadNetwork P3293 FINISHED
Object A968
A968 is a primary road in Shetland, Scotland, forming a key transport link between several of the islands’ main settlements.
 E1567500 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: A968 | Statement: [Mainland, Shetland, hasRoadNetwork, A968]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: A968
Context triple: [Mainland, Shetland, hasRoadNetwork, A968]
  • A. A96
    The A96 is a major trunk road in northeast Scotland that connects the cities of Aberdeen and Inverness, serving as a key route for regional traffic and commerce.
  • B. A96
    A96 is a major German autobahn in southern Bavaria that connects Munich with Lindau near the Austrian and Swiss borders.
  • C. A9
    A9 is a major German autobahn that runs north–south, connecting Berlin with Munich and passing through regions such as Middle Franconia.
  • D. A9
    A9 is a major Swiss motorway that runs across the southwestern part of the country, connecting key regions in Valais and linking to international routes.
  • E. A9
    A9 is the IATA airline designator assigned to Georgian Airways, the flag carrier of Georgia.
  • 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: A968
Triple: [Mainland, Shetland, hasRoadNetwork, A968]
Generated description
A968 is a primary road in Shetland, Scotland, forming a key transport link between several of the islands’ main settlements.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: A968
Target entity description: A968 is a primary road in Shetland, Scotland, forming a key transport link between several of the islands’ main settlements.
  • A. A96
    The A96 is a major trunk road in northeast Scotland that connects the cities of Aberdeen and Inverness, serving as a key route for regional traffic and commerce.
  • B. A96
    A96 is a major German autobahn in southern Bavaria that connects Munich with Lindau near the Austrian and Swiss borders.
  • C. A9
    A9 is a major Swiss motorway that runs across the southwestern part of the country, connecting key regions in Valais and linking to international routes.
  • D. A9
    A9 is a Portuguese motorway that serves as an outer ring road around Lisbon, connecting several major radial highways and easing traffic around the capital.
  • E. A9
    A9 is a major German autobahn that runs north–south, connecting Berlin with Munich and passing through regions such as Middle Franconia.
  • 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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18512df708190a6892e743a289c74 completed April 29, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf2ba6cd48190adfde89532b51f43 completed May 19, 2026, 5:18 a.m.
NEDg Description generation batch_6a0c0332a0288190a51b29aa03e1969a completed May 19, 2026, 6:29 a.m.
NED2 Entity disambiguation (via description) batch_6a0c04d4722c8190967b59808f6c1e36 completed May 19, 2026, 6:36 a.m.
Created at: April 17, 2026, 3:53 p.m.