Triple

T9140491
Position Surface form Disambiguated ID Type / Status
Subject Middlesbrough E219312 entity
Predicate postcodeArea P920 FINISHED
Object TS
TS is the UK postcode area covering Middlesbrough and surrounding parts of North East England.
 E728919 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: TS | Statement: [Middlesbrough, postcodeArea, TS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TS
Context triple: [Middlesbrough, postcodeArea, TS]
  • A. TS
    TS is the official vehicle registration code used on motor vehicles registered in the Indian state of Telangana.
  • B. TS
    TS is the Technical Secretariat of the Organisation for the Prohibition of Chemical Weapons, the body responsible for implementing and verifying compliance with the Chemical Weapons Convention.
  • C. TS
    TS is the vehicle registration code used on license plates for the Province of Trieste in northeastern Italy.
  • D. TS
    TS is the common abbreviation for Windows Terminal Services, Microsoft’s legacy remote desktop and application virtualization technology for Windows servers.
  • E. TS
    TS is the IATA airline designator assigned to Air Transat, a Canadian leisure airline based in Montreal.
  • 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: TS
Triple: [Middlesbrough, postcodeArea, TS]
Generated description
TS is the UK postcode area covering Middlesbrough and surrounding parts of North East England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TS
Target entity description: TS is the UK postcode area covering Middlesbrough and surrounding parts of North East England.
  • A. TS chosen
    TS is a postcode area in northeastern England covering parts of Teesside, including towns such as Stockton-on-Tees and Middlesbrough.
  • B. TS
    TS is the vehicle registration code used on license plates for the Traunstein district in Bavaria, Germany.
  • C. TS
    TS is the vehicle registration code used on license plates for the Province of Trieste in northeastern Italy.
  • D. TS
    TS is the common abbreviation for Trabzonspor, a major Turkish professional football club based in the city of Trabzon.
  • E. TS
    TS is the official vehicle registration code used on motor vehicles registered in the Indian state of Telangana.
  • F. None of above.

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_69ca83e012288190a5771058adbaabd2 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca8f2537881908956a9b0516e2d49 completed April 1, 2026, 5:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0480ee2f081908ed98844784e465c completed April 3, 2026, 11:06 p.m.
NEDg Description generation batch_69d04935d4e88190acb4d65a2dc2bc8a completed April 3, 2026, 11:11 p.m.
NED2 Entity disambiguation (via description) batch_69d049e6c4cc81909e08b5aaed9a88dc completed April 3, 2026, 11:14 p.m.
Created at: March 30, 2026, 7:19 p.m.