Triple

T16857306
Position Surface form Disambiguated ID Type / Status
Subject Angel Underground station E409817 entity
Predicate stationCode P1289 FINISHED
Object AGL
AGL is the three-letter station code used to identify Angel Underground station on the London Underground network.
 E1236396 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: AGL | Statement: [Angel Underground station, stationCode, AGL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AGL
Context triple: [Angel Underground station, stationCode, AGL]
  • A. AGL
    AGL is an open-source automotive software platform and collaborative project under the Linux Foundation focused on building a unified in-vehicle infotainment and connected car system.
  • B. AG
    AG is the two-letter ISO 3166-1 alpha-2 country code assigned to Antigua and Barbuda.
  • C. AG
    AG is the vehicle registration code used on license plates for cars registered in Argeș County, Romania.
  • D. AG
    AG is the common abbreviation for the Christian missions organization To the Nations.
  • E. AG
    AG is the standard abbreviation for the United States Attorney General, the chief law enforcement officer and head of the U.S. Department of Justice.
  • 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: AGL
Triple: [Angel Underground station, stationCode, AGL]
Generated description
AGL is the three-letter station code used to identify Angel Underground station on the London Underground network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AGL
Target entity description: AGL is the three-letter station code used to identify Angel Underground station on the London Underground network.
  • A. AGL
    AGL is an open-source automotive software platform and collaborative project under the Linux Foundation focused on building a unified in-vehicle infotainment and connected car system.
  • B. AG
    AG is the common abbreviation for the Christian missions organization To the Nations.
  • C. AG
    AG is the two-letter ISO 3166-1 alpha-2 country code assigned to Antigua and Barbuda.
  • D. AG
    AG is the vehicle registration code used on license plates for cars registered in Argeș County, Romania.
  • E. AG
    AG is a common abbreviation for a German-language joint-stock company structure known as "Aktiengesellschaft."
  • 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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b37e34b88190bb4468424e2edf2d completed April 18, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb2337348190ae79dc4b188c94cf completed May 10, 2026, 5:06 p.m.
NEDg Description generation batch_6a00bbe7e4c4819081d0bfd1ac427c49 completed May 10, 2026, 5:10 p.m.
NED2 Entity disambiguation (via description) batch_6a00bc73e4e88190a8327ba48174f923 completed May 10, 2026, 5:12 p.m.
Created at: April 10, 2026, 5:24 a.m.