Triple

T13105304
Position Surface form Disambiguated ID Type / Status
Subject SAM.gov E310827 entity
Predicate abbreviation P43 FINISHED
Object SAM
SAM is the U.S. federal government’s central online system for registering entities to do business with federal agencies and for managing related procurement and award data.
 E1023342 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: SAM | Statement: [SAM.gov, abbreviation, SAM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SAM
Context triple: [SAM.gov, abbreviation, SAM]
  • A. SAM
    SAM is an analytical laboratory aboard NASA's Curiosity rover that studies Martian rocks, soil, and atmosphere to determine their chemical and organic composition.
  • B. SAM
    SAM is the commonly used abbreviation for the South Australian Museum, a major natural history and cultural institution located in Adelaide, Australia.
  • C. SAM
    SAM is the three-letter international code used to represent the Samoa national rugby league team in official competitions and records.
  • D. SAM
    SAM is the official FIFA trigramme used to represent the Samoa national under-20 football team in international competitions and records.
  • E. SAM
    SAM is an online training and assessment platform used primarily in education for teaching and evaluating computer and digital literacy skills.
  • 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: SAM
Triple: [SAM.gov, abbreviation, SAM]
Generated description
SAM is the U.S. federal government’s central online system for registering entities to do business with federal agencies and for managing related procurement and award data.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SAM
Target entity description: SAM is the U.S. federal government’s central online system for registering entities to do business with federal agencies and for managing related procurement and award data.
  • A. SAM
    SAM is an online training and assessment platform used primarily in education for teaching and evaluating computer and digital literacy skills.
  • B. SAM
    SAM is the official FIFA trigramme used to represent the Samoa national under-20 football team in international competitions and records.
  • C. SAM
    SAM is an analytical laboratory aboard NASA's Curiosity rover that studies Martian rocks, soil, and atmosphere to determine their chemical and organic composition.
  • D. SAM
    SAM is the commonly used abbreviation for the South Australian Museum, a major natural history and cultural institution located in Adelaide, Australia.
  • E. SAM
    SAM is the three-letter international code used to represent the Samoa national rugby league team in official competitions and records.
  • 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_69d806a872d08190a329806f8ff30df4 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98154c9f48190aeca779d97151759 completed April 10, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e27a325c8190a5c0f1a582340078 completed May 3, 2026, 5:51 a.m.
NEDg Description generation batch_69f6e6a8b15081908d80cd63b0c423f6 completed May 3, 2026, 6:09 a.m.
NED2 Entity disambiguation (via description) batch_69f6e7490cc48190b596338cd3a0fd22 completed May 3, 2026, 6:12 a.m.
Created at: April 9, 2026, 9:05 p.m.