Triple

T13644060
Position Surface form Disambiguated ID Type / Status
Subject Mines Advisory Group E326056 entity
Predicate abbreviation P43 FINISHED
Object MAG
MAG is an international humanitarian organization that works to clear landmines and unexploded ordnance and make land safe for communities affected by conflict.
 E1053684 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: MAG | Statement: [Mines Advisory Group, abbreviation, MAG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MAG
Context triple: [Mines Advisory Group, abbreviation, MAG]
  • A. MAG
    MAG is a major British airport operator that owns and manages several UK airports, including Manchester Airport.
  • B. MAG
    MAG is the magnetometer instrument aboard the European Space Agency’s Venus Express spacecraft, designed to measure Venus’s magnetic field and its interaction with the solar wind.
  • C. MAG
    MAG is the abbreviated name used to represent Magic Gaming, the NBA 2K League affiliate of the Orlando Magic.
  • D. MAG
    MAG is the parent company of Malaysia Airlines and related aviation businesses, overseeing the group’s airline, cargo, and aviation services operations.
  • E. MAG
    MAG is the Multistakeholder Advisory Group that supports and advises the United Nations-convened Internet Governance Forum on its program and agenda.
  • 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: MAG
Triple: [Mines Advisory Group, abbreviation, MAG]
Generated description
MAG is an international humanitarian organization that works to clear landmines and unexploded ordnance and make land safe for communities affected by conflict.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MAG
Target entity description: MAG is an international humanitarian organization that works to clear landmines and unexploded ordnance and make land safe for communities affected by conflict.
  • A. MAG
    MAG is a major British airport operator that owns and manages several UK airports, including Manchester Airport.
  • B. MAG
    MAG is the abbreviated name used to represent Magic Gaming, the NBA 2K League affiliate of the Orlando Magic.
  • C. MAG
    MAG is the parent company of Malaysia Airlines and related aviation businesses, overseeing the group’s airline, cargo, and aviation services operations.
  • D. MAG
    MAG is the magnetometer instrument aboard the European Space Agency’s Venus Express spacecraft, designed to measure Venus’s magnetic field and its interaction with the solar wind.
  • E. MAG
    MAG is the Multistakeholder Advisory Group that supports and advises the United Nations-convened Internet Governance Forum on its program and agenda.
  • 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_69d8076beddc8190a53156f5bea77f5e completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc5ac2af88190976abe6606994eef completed April 12, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78af74a548190bc8bbe1a1410997a completed May 3, 2026, 5:50 p.m.
NEDg Description generation batch_69f78bd52b748190ab483ec7634a6549 completed May 3, 2026, 5:54 p.m.
NED2 Entity disambiguation (via description) batch_69f78d277c5c8190970cb3cd0fd32905 completed May 3, 2026, 6 p.m.
Created at: April 9, 2026, 9:51 p.m.