Triple

T21005537
Position Surface form Disambiguated ID Type / Status
Subject Midea Group E517403 entity
Predicate hasSubsidiary P254 FINISHED
Object GMCC
GMCC is a Chinese manufacturer best known for producing compressors and related components for air conditioners and refrigeration systems.
 E1462450 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: GMCC | Statement: [Midea Group, hasSubsidiary, GMCC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GMCC
Context triple: [Midea Group, hasSubsidiary, GMCC]
  • A. MCC
    MCC is the former name of the Horizon League, an NCAA Division I collegiate athletic conference in the United States.
  • B. MCC
    MCC is the commonly used abbreviation for Middlesex College, a public community college serving students with two-year degree and certificate programs.
  • C. MCC
    MCC is the abbreviated name of Belgium’s naval branch within the Belgian Armed Forces.
  • D. MCC
    MCC is a U.S. foreign aid agency that provides time-limited grants to promote economic growth, reduce poverty, and strengthen institutions in developing countries.
  • E. MCC
    MCC is the Mars Colour Camera, an imaging instrument aboard India’s Mars Orbiter Mission used to capture color photographs of the Martian surface and atmosphere.
  • 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: GMCC
Triple: [Midea Group, hasSubsidiary, GMCC]
Generated description
GMCC is a Chinese manufacturer best known for producing compressors and related components for air conditioners and refrigeration systems.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GMCC
Target entity description: GMCC is a Chinese manufacturer best known for producing compressors and related components for air conditioners and refrigeration systems.
  • A. MCC
    MCC is the former name of the Horizon League, an NCAA Division I collegiate athletic conference in the United States.
  • B. MCC
    MCC is the commonly used abbreviation for Middlesex College, a public community college serving students with two-year degree and certificate programs.
  • C. MCC
    MCC is the abbreviated name of Belgium’s naval branch within the Belgian Armed Forces.
  • D. MCC
    MCC is a U.S. foreign aid agency that provides time-limited grants to promote economic growth, reduce poverty, and strengthen institutions in developing countries.
  • E. MCC
    MCC is a historic and influential cricket club based at Lord’s in London, long regarded as the guardian of the Laws of Cricket.
  • 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_69e0b50192308190a284fcc89dd23a49 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc3b25ec8190aa4530d1f0bb2b9e completed April 21, 2026, 4:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a093b580244819081930a1ab0a78f72 completed May 17, 2026, 3:51 a.m.
NEDg Description generation batch_6a09403c9bac81908f15cea8b0b44239 completed May 17, 2026, 4:12 a.m.
NED2 Entity disambiguation (via description) batch_6a0940b7e9e081908853730ea291605d completed May 17, 2026, 4:14 a.m.
Created at: April 16, 2026, 1:52 p.m.