Triple

T14509552
Position Surface form Disambiguated ID Type / Status
Subject Metro Inc. E340358 entity
Predicate tradesUnderTicker P1447 FINISHED
Object MRU
MRU is the stock ticker symbol for Metro Inc., a major Canadian food and pharmacy retail company.
E1105580 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: MRU | Statement: [Metro Inc., tradesUnderTicker, MRU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MRU
Context triple: [Metro Inc., tradesUnderTicker, MRU]
  • A. MRU
    MRU is the three-letter ISO 4217 currency code for the Mauritanian ouguiya, the official currency of Mauritania.
  • B. MRU
    MRU is the abbreviation for the Mano River Union, a regional organization that promotes economic cooperation and integration among West African countries along the Mano River.
  • C. MRIT
    MRIT is an abbreviation for the Matsushita Research Institute Tokyo, a Japanese research organization historically associated with Panasonic’s advanced technology and electronics R&D.
  • D. MRIA
    MRIA is the post-nominal title indicating membership of the Royal Irish Academy, an all-Ireland body of distinguished scholars and scientists.
  • E. MRIA
    MRIA is the abbreviation for Mattala Rajapaksa International Airport, a major international airport located in southern Sri Lanka.
  • 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: MRU
Triple: [Metro Inc., tradesUnderTicker, MRU]
Generated description
MRU is the stock ticker symbol for Metro Inc., a major Canadian food and pharmacy retail company.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MRU
Target entity description: MRU is the stock ticker symbol for Metro Inc., a major Canadian food and pharmacy retail company.
  • A. MRU
    MRU is the three-letter ISO 4217 currency code for the Mauritanian ouguiya, the official currency of Mauritania.
  • B. MRU
    MRU is the abbreviation for the Mano River Union, a regional organization that promotes economic cooperation and integration among West African countries along the Mano River.
  • C. MRIT
    MRIT is an abbreviation for the Matsushita Research Institute Tokyo, a Japanese research organization historically associated with Panasonic’s advanced technology and electronics R&D.
  • D. MRIA
    MRIA is the abbreviation for Mattala Rajapaksa International Airport, a major international airport located in southern Sri Lanka.
  • E. MRIA
    MRIA is the post-nominal title indicating membership of the Royal Irish Academy, an all-Ireland body of distinguished scholars and scientists.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de94e5b7b48190878be271840c265b completed April 14, 2026, 7:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8aaeaf40819087fa0db989813e02 completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8b5929c08190ae4596a23857ed06 completed May 8, 2026, 7:06 a.m.
NED2 Entity disambiguation (via description) batch_69fd8beb5d608190b4825ccb0935f041 completed May 8, 2026, 7:08 a.m.
Created at: April 10, 2026, 1:21 a.m.