Triple

T6434570
Position Surface form Disambiguated ID Type / Status
Subject Chesapeake Bay Maritime Museum E129861 entity
Predicate shortName P43 FINISHED
Object CBMM
CBMM is a museum in St. Michaels, Maryland dedicated to preserving and interpreting the maritime history, culture, and environment of the Chesapeake Bay.
 E591887 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: CBMM | Statement: [Chesapeake Bay Maritime Museum, shortName, CBMM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CBMM
Context triple: [Chesapeake Bay Maritime Museum, shortName, CBMM]
  • A. HCMM
    HCMM is the ICAO airport code assigned to Aden Adde International Airport, the main international airport serving Mogadishu, Somalia.
  • B. BMBF
    BMBF is the German Federal Ministry responsible for national policy and funding in education, science, and research.
  • C. CBb
    CBb is the Dutch Trade and Industry Appeals Tribunal, a specialized administrative court in the Netherlands that handles disputes in economic and regulatory matters.
  • D. CB
    CB is the post-nominal abbreviation indicating appointment as a Companion of the Order of the Bath, a British order of chivalry.
  • E. CB
    CB is a UK postcode area covering Cambridge and surrounding parts of Cambridgeshire and nearby regions.
  • 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: CBMM
Triple: [Chesapeake Bay Maritime Museum, shortName, CBMM]
Generated description
CBMM is a museum in St. Michaels, Maryland dedicated to preserving and interpreting the maritime history, culture, and environment of the Chesapeake Bay.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CBMM
Target entity description: CBMM is a museum in St. Michaels, Maryland dedicated to preserving and interpreting the maritime history, culture, and environment of the Chesapeake Bay.
  • A. HCMM
    HCMM is the ICAO airport code assigned to Aden Adde International Airport, the main international airport serving Mogadishu, Somalia.
  • B. BMBF
    BMBF is the German Federal Ministry responsible for national policy and funding in education, science, and research.
  • C. CBb
    CBb is the Dutch Trade and Industry Appeals Tribunal, a specialized administrative court in the Netherlands that handles disputes in economic and regulatory matters.
  • D. CB
    CB is the post-nominal abbreviation indicating appointment as a Companion of the Order of the Bath, a British order of chivalry.
  • E. CB
    CB is a UK postcode area covering Cambridge and surrounding parts of Cambridgeshire and nearby regions.
  • 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_69c0084caac48190a7bc2ad8ba44536f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0693f73ec8190883470b57f8141aa completed March 22, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640efd490819084b3b67b3b0680b6 completed March 27, 2026, 8:33 a.m.
NEDg Description generation batch_69c6420e3fe48190aef959cb7ab1e0d3 completed March 27, 2026, 8:38 a.m.
NED2 Entity disambiguation (via description) batch_69c642a344e48190bccb0f0d122fca4c completed March 27, 2026, 8:41 a.m.
Created at: March 22, 2026, 4:45 p.m.