Triple

T583487
Position Surface form Disambiguated ID Type / Status
Subject Mont Blanc Tunnel E15106 entity
Predicate operator P179 FINISHED
Object ATMB
ATMB is a French company responsible for managing and operating major alpine transport infrastructure, including the Mont Blanc Tunnel.
 E72897 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: ATMB | Statement: [Mont Blanc Tunnel, operator, ATMB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ATMB
Context triple: [Mont Blanc Tunnel, operator, ATMB]
  • A. AMTK
    AMTK is the reporting mark used by Amtrak, the United States’ national passenger railroad service, to identify its locomotives and rolling stock.
  • B. AMA
    AMA is the leading professional association and lobbying group representing physicians and medical students in the United States.
  • C. AMM
    AMM is the commonly used abbreviation for the APEC Ministerial Meeting, the annual gathering of Asia-Pacific Economic Cooperation foreign and trade ministers.
  • D. AMRO
    AMRO is the World Health Organization’s Regional Office responsible for public health leadership and coordination across the Americas.
  • E. ABJ
    ABJ is the vehicle registration code used for motor vehicles registered in Abuja, the capital city of Nigeria.
  • 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: ATMB
Triple: [Mont Blanc Tunnel, operator, ATMB]
Generated description
ATMB is a French company responsible for managing and operating major alpine transport infrastructure, including the Mont Blanc Tunnel.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ATMB
Target entity description: ATMB is a French company responsible for managing and operating major alpine transport infrastructure, including the Mont Blanc Tunnel.
  • A. AMTK
    AMTK is the reporting mark used by Amtrak, the United States’ national passenger railroad service, to identify its locomotives and rolling stock.
  • B. AMA
    AMA is the leading professional association and lobbying group representing physicians and medical students in the United States.
  • C. AMM
    AMM is the commonly used abbreviation for the APEC Ministerial Meeting, the annual gathering of Asia-Pacific Economic Cooperation foreign and trade ministers.
  • D. AMRO
    AMRO is the World Health Organization’s Regional Office responsible for public health leadership and coordination across the Americas.
  • E. ABJ
    ABJ is the vehicle registration code used for motor vehicles registered in Abuja, the capital city of Nigeria.
  • 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_69a4935783b8819082b77726ec10cc42 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49b8745c88190af9672e5fe8396c3 completed March 1, 2026, 8:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69a508a1cc788190a0906bfd876e510e completed March 2, 2026, 3:48 a.m.
NEDg Description generation batch_69a50acbc7948190839d73bf48af0a67 completed March 2, 2026, 3:58 a.m.
NED2 Entity disambiguation (via description) batch_69a50b5abad08190b5abab497c61952b completed March 2, 2026, 4 a.m.
Created at: March 1, 2026, 7:33 p.m.