Triple

T19776572
Position Surface form Disambiguated ID Type / Status
Subject South African Maritime Safety Authority E475015 entity
Predicate abbreviation P43 FINISHED
Object SAMSA
SAMSA is the national agency responsible for regulating and promoting maritime safety, security, and environmental protection in South Africa’s waters.
 E1394157 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: SAMSA | Statement: [South African Maritime Safety Authority, abbreviation, SAMSA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SAMSA
Context triple: [South African Maritime Safety Authority, abbreviation, SAMSA]
  • A. SAMHS
    SAMHS is the branch of the South African National Defence Force responsible for providing comprehensive medical and health support to military personnel.
  • B. SAMO
    SAMO was the graffiti tag and artistic persona used by Jean-Michel Basquiat in late-1970s New York City, known for its cryptic, poetic street art.
  • C. SAMS
    SAMS is the Swiss Academy of Medical Sciences, a national institution that promotes medical research, ethics, and healthcare policy in Switzerland.
  • D. SAM
    SAM is the commonly used abbreviation for Stade Athlétique Montluçonnais, a French rugby union club.
  • E. SAM
    SAM is the common abbreviation for Sigma Alpha Mu, a historically Jewish but now inclusive collegiate social fraternity founded in 1909.
  • 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: SAMSA
Triple: [South African Maritime Safety Authority, abbreviation, SAMSA]
Generated description
SAMSA is the national agency responsible for regulating and promoting maritime safety, security, and environmental protection in South Africa’s waters.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SAMSA
Target entity description: SAMSA is the national agency responsible for regulating and promoting maritime safety, security, and environmental protection in South Africa’s waters.
  • A. SAMHS
    SAMHS is the branch of the South African National Defence Force responsible for providing comprehensive medical and health support to military personnel.
  • B. SAMO
    SAMO was the graffiti tag and artistic persona used by Jean-Michel Basquiat in late-1970s New York City, known for its cryptic, poetic street art.
  • C. SAMS
    SAMS is the Swiss Academy of Medical Sciences, a national institution that promotes medical research, ethics, and healthcare policy in Switzerland.
  • D. SAM
    SAM is the commonly used abbreviation for Stade Athlétique Montluçonnais, a French rugby union club.
  • E. SAM
    SAM is the common abbreviation for Sigma Alpha Mu, a historically Jewish but now inclusive collegiate social fraternity founded in 1909.
  • 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65360cca08190957c36b1a440542c completed April 20, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07bd78ce00819097b4df2bff211b31 completed May 16, 2026, 12:42 a.m.
NEDg Description generation batch_6a07be65daf88190a0ed2b6f8075141a completed May 16, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_6a07bf1be9648190bac752e8a6ca12bc completed May 16, 2026, 12:49 a.m.
Created at: April 10, 2026, 1:48 p.m.