Triple

T7113650
Position Surface form Disambiguated ID Type / Status
Subject Bezos Expeditions E165762 entity
Predicate notableInvestmentIn P17330 FINISHED
Object MFG.com
MFG.com is an online manufacturing marketplace that connects buyers of custom manufactured parts with a global network of suppliers and machine shops.
 E642876 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: MFG.com | Statement: [Bezos Expeditions, notableInvestmentIn, MFG.com]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MFG.com
Context triple: [Bezos Expeditions, notableInvestmentIn, MFG.com]
  • A. MGA
    MGA is the IATA airport code for Augusto C. Sandino International Airport, the main international gateway serving Managua, Nicaragua.
  • B. MGA
    MGA is a public university in Georgia, United States, offering a range of undergraduate and graduate programs across multiple campuses.
  • C. MGA
    MGA is the official ISO 4217 currency code for the Malagasy ariary, the national currency of Madagascar.
  • D. MGA
    MGA is the commonly used abbreviation for the Maryland General Assembly, the state’s bicameral legislative body.
  • E. MANN
    MANN is a major Italian archaeological museum in Naples renowned for its extensive collections of Greek, Roman, and particularly Pompeian antiquities.
  • 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: MFG.com
Triple: [Bezos Expeditions, notableInvestmentIn, MFG.com]
Generated description
MFG.com is an online manufacturing marketplace that connects buyers of custom manufactured parts with a global network of suppliers and machine shops.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MFG.com
Target entity description: MFG.com is an online manufacturing marketplace that connects buyers of custom manufactured parts with a global network of suppliers and machine shops.
  • A. MGA
    MGA is the IATA airport code for Augusto C. Sandino International Airport, the main international gateway serving Managua, Nicaragua.
  • B. MGA
    MGA is the official ISO 4217 currency code for the Malagasy ariary, the national currency of Madagascar.
  • C. MGA
    MGA is the commonly used abbreviation for the Maryland General Assembly, the state’s bicameral legislative body.
  • D. MGA
    MGA is a public university in Georgia, United States, offering a range of undergraduate and graduate programs across multiple campuses.
  • E. MANN
    MANN is a major Italian archaeological museum in Naples renowned for its extensive collections of Greek, Roman, and particularly Pompeian antiquities.
  • 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_69c6888120f081908f8f01b201dc4a4c completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e7759a048190815689298befa8d7 completed March 27, 2026, 8:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79cbc35d48190974e207eb98dcbe3 completed March 28, 2026, 9:17 a.m.
NEDg Description generation batch_69c79d31a9e8819096e6a3040b1852a9 completed March 28, 2026, 9:19 a.m.
NED2 Entity disambiguation (via description) batch_69c79dcae54c8190b06e687236373f68 completed March 28, 2026, 9:22 a.m.
Created at: March 27, 2026, 2:43 p.m.