Triple

T17408889
Position Surface form Disambiguated ID Type / Status
Subject London Controlling Section E423293 entity
Predicate precededBy P97 FINISHED
Object MI(R)
MI(R) was a secret British military intelligence unit responsible for planning deception operations during the early years of the Second World War.
 E1267675 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: MI(R) | Statement: [London Controlling Section, precededBy, MI(R)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MI(R)
Context triple: [London Controlling Section, precededBy, MI(R)]
  • A. MI
    MI is the vehicle registration code used on license plates for vehicles registered in Minden, a town in Germany.
  • B. MI
    MI is the Mathematical Institute of Leiden University, a department focused on research and education in mathematics.
  • C. MI
    MI is the vehicle registration code used on license plates for vehicles registered in the Phthiotis regional unit of Greece.
  • D. MI
    MI is the official two-letter United States Postal Service abbreviation for the state of Michigan.
  • E. MI
    MI is the commonly used abbreviation for the Mumbai Indians, a prominent franchise cricket team in the Indian Premier League.
  • 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: MI(R)
Triple: [London Controlling Section, precededBy, MI(R)]
Generated description
MI(R) was a secret British military intelligence unit responsible for planning deception operations during the early years of the Second World War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MI(R)
Target entity description: MI(R) was a secret British military intelligence unit responsible for planning deception operations during the early years of the Second World War.
  • A. MI
    MI is the Mathematical Institute of Leiden University, a department focused on research and education in mathematics.
  • B. MI
    MI is the vehicle registration code used on license plates for vehicles registered in Minden, a town in Germany.
  • C. MI
    MI is the official two-letter United States Postal Service abbreviation for the state of Michigan.
  • D. MI
    MI is the commonly used abbreviation for the Mumbai Indians, a prominent franchise cricket team in the Indian Premier League.
  • E. MI
    MI is the vehicle registration code used on license plates for vehicles registered in the Phthiotis regional unit of Greece.
  • 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_69d889d7d27c819088486ce3f0627fa1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43b0990f48190b62d73087ae1a0d7 completed April 19, 2026, 2:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01a7fbf3e88190972b3e8141d07a3b completed May 11, 2026, 9:57 a.m.
NEDg Description generation batch_6a01aa035f2c8190bd2619a14c9497d5 completed May 11, 2026, 10:05 a.m.
NED2 Entity disambiguation (via description) batch_6a01aa6e98088190b01f16114ccde2eb completed May 11, 2026, 10:07 a.m.
Created at: April 10, 2026, 5:46 a.m.