Triple

T4943449
Position Surface form Disambiguated ID Type / Status
Subject SN 1987A E110990 entity
Predicate neutrinoDetectors P13781 FINISHED
Object IMB
IMB was a large underground water Cherenkov detector in the United States, originally built to search for proton decay and later known for detecting neutrinos from supernova SN 1987A.
 E481645 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: IMB | Statement: [SN 1987A, neutrinoDetectors, IMB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: IMB
Context triple: [SN 1987A, neutrinoDetectors, IMB]
  • A. IMM
    IMM is a research organization focused on advancing molecular nanotechnology and atomically precise manufacturing.
  • B. IBI
    IBI is an academic institute focused on advancing research, education, and practice in business innovation and entrepreneurship.
  • C. IMAs
    IMAs are military reservists assigned individually to active-duty units to provide specialized skills and surge support during contingencies or high-demand periods.
  • D. IMBA
    IMBA is an International Master of Business Administration program offered by the Schulich School of Business, focusing on globally oriented management education and cross-cultural business skills.
  • E. IM
    IM is the two-letter ISO 3166-1 alpha-2 country code assigned to the Isle of Man.
  • 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: IMB
Triple: [SN 1987A, neutrinoDetectors, IMB]
Generated description
IMB was a large underground water Cherenkov detector in the United States, originally built to search for proton decay and later known for detecting neutrinos from supernova SN 1987A.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: IMB
Target entity description: IMB was a large underground water Cherenkov detector in the United States, originally built to search for proton decay and later known for detecting neutrinos from supernova SN 1987A.
  • A. IMM
    IMM is a research organization focused on advancing molecular nanotechnology and atomically precise manufacturing.
  • B. IBI
    IBI is an academic institute focused on advancing research, education, and practice in business innovation and entrepreneurship.
  • C. IMAs
    IMAs are military reservists assigned individually to active-duty units to provide specialized skills and surge support during contingencies or high-demand periods.
  • D. IMBA
    IMBA is an International Master of Business Administration program offered by the Schulich School of Business, focusing on globally oriented management education and cross-cultural business skills.
  • E. IM
    IM is the two-letter ISO 3166-1 alpha-2 country code assigned to the Isle of Man.
  • 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_69bd441721cc819085c7e33fe0876818 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd716520f08190862249efb2058fd4 completed March 20, 2026, 4:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77c421288190bcc2d9bfdfff7198 completed March 21, 2026, 10:49 a.m.
NEDg Description generation batch_69be79127e80819088a97e674991fc8b completed March 21, 2026, 10:55 a.m.
NED2 Entity disambiguation (via description) batch_69be7990fd048190b3d1acaa6e3bce90 completed March 21, 2026, 10:57 a.m.
Created at: March 20, 2026, 1:31 p.m.