Triple

T20884050
Position Surface form Disambiguated ID Type / Status
Subject Combustion Institute E514225 entity
Predicate hasAbbreviation P43 FINISHED
Object CI
CI is the standard abbreviation for The Combustion Institute, an international scientific society dedicated to advancing research and knowledge in combustion science and technology.
 E1455276 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: CI | Statement: [Combustion Institute, hasAbbreviation, CI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CI
Context triple: [Combustion Institute, hasAbbreviation, CI]
  • A. CI
    CI is the IATA airline designator for China Airlines, the flag carrier of Taiwan.
  • B. CI
    CI is the commonly used abbreviation for California State University Channel Islands, a public university in Camarillo, California.
  • C. CI
    CI is the station code used to identify Central Islip station on the Long Island Rail Road.
  • D. CI
    CI is the ISO 3166-1 alpha-2 country code for Côte d'Ivoire (Ivory Coast), a West African nation on the Gulf of Guinea.
  • E. CI
    CI is the abbreviation for the U.S. Department of Energy’s Office of Congressional and Intergovernmental Affairs, which manages the agency’s relationships with Congress and other government entities.
  • 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: CI
Triple: [Combustion Institute, hasAbbreviation, CI]
Generated description
CI is the standard abbreviation for The Combustion Institute, an international scientific society dedicated to advancing research and knowledge in combustion science and technology.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CI
Target entity description: CI is the standard abbreviation for The Combustion Institute, an international scientific society dedicated to advancing research and knowledge in combustion science and technology.
  • A. CI
    CI is the abbreviation for the U.S. Department of Energy’s Office of Congressional and Intergovernmental Affairs, which manages the agency’s relationships with Congress and other government entities.
  • B. CI
    CI is the common abbreviation for the Coppa Italia, Italy’s premier national football cup competition.
  • C. CI
    CI is the commonly used abbreviation for California State University Channel Islands, a public university in Camarillo, California.
  • D. CI
    CI is the ISO 3166-1 alpha-2 country code for Côte d'Ivoire (Ivory Coast), a West African nation on the Gulf of Guinea.
  • E. CI
    CI is the station code used to identify Central Islip station on the Long Island Rail Road.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c67bd32c819097301e330e358c49 completed April 21, 2026, 12:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0913a67fec819093ea6b8388f983f0 completed May 17, 2026, 1:02 a.m.
NEDg Description generation batch_6a0914d5ffb081909f7eca2593de8a10 completed May 17, 2026, 1:07 a.m.
NED2 Entity disambiguation (via description) batch_6a0915665ec081909695a6c4aba50dbc completed May 17, 2026, 1:09 a.m.
Created at: April 16, 2026, 12:46 p.m.