Triple

T17204519
Position Surface form Disambiguated ID Type / Status
Subject Ambelokipi metro station E417564 entity
Predicate hasStationCode P1289 FINISHED
Object AMB
AMB is the station code for Ambelokipi, a metro station on the Athens Metro network in Greece.
 E1256751 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: AMB | Statement: [Ambelokipi metro station, hasStationCode, AMB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AMB
Context triple: [Ambelokipi metro station, hasStationCode, AMB]
  • A. AMB
    AMB is the IATA airport code for RAAF Base Amberley, a major Royal Australian Air Force base in Queensland, Australia.
  • B. Amb
    Amb is a town in the Una district of Himachal Pradesh, India, known as a local commercial and transportation hub.
  • C. AMA
    AMA is the three-letter IATA airport code for Rick Husband Amarillo International Airport in Amarillo, Texas.
  • D. AMA
    AMA is the commonly used abbreviation for Japan’s Antimonopoly Act, the core law regulating competition and prohibiting monopolistic practices in the country.
  • E. AMA
    AMA is the leading professional association and lobbying group representing physicians and medical students in the United States.
  • 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: AMB
Triple: [Ambelokipi metro station, hasStationCode, AMB]
Generated description
AMB is the station code for Ambelokipi, a metro station on the Athens Metro network in Greece.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AMB
Target entity description: AMB is the station code for Ambelokipi, a metro station on the Athens Metro network in Greece.
  • A. AMB
    AMB is the IATA airport code for RAAF Base Amberley, a major Royal Australian Air Force base in Queensland, Australia.
  • B. Amb
    Amb is a town in the Una district of Himachal Pradesh, India, known as a local commercial and transportation hub.
  • C. AMA
    AMA is the three-letter IATA airport code for Rick Husband Amarillo International Airport in Amarillo, Texas.
  • D. AMA
    AMA is the commonly used abbreviation for Japan’s Antimonopoly Act, the core law regulating competition and prohibiting monopolistic practices in the country.
  • E. AMA
    AMA is the leading professional association and lobbying group representing physicians and medical students in the United States.
  • 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_69d886d6ba8c819093215917b3d01689 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42db1e01c81909db0491fd9f49bed completed April 19, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a015fde8ba08190ae88dc9ea3366a68 completed May 11, 2026, 4:49 a.m.
NEDg Description generation batch_6a0161b31540819098aa6275f96433ad completed May 11, 2026, 4:57 a.m.
NED2 Entity disambiguation (via description) batch_6a016299d9ac8190be74d5db0d28ea36 completed May 11, 2026, 5:01 a.m.
Created at: April 10, 2026, 5:38 a.m.