Triple

T26870824
Position Surface form Disambiguated ID Type / Status
Subject Harry Markopolos E676604 entity
Predicate claimedMadoffMaxSize P166630 FINISHED
Object approximately $50 billion fraud LITERAL FINISHED

How this triple was built (2 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: approximately $50 billion fraud | Statement: [Harry Markopolos, claimedMadoffMaxSize, approximately $50 billion fraud]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: claimedMadoffMaxSize
Context triple: [Harry Markopolos, claimedMadoffMaxSize, approximately $50 billion fraud]
  • A. maximumGrantAmount
    Indicates the highest monetary value that can be awarded or granted under a specific grant, program, or agreement.
  • B. capitalClaimed
    Indicates that an entity asserts or designates another entity as its capital.
  • C. hasMaximumBalanceLimit
    Indicates that there is an upper bound on the balance that an account or entity is allowed to hold.
  • D. authorizedBondAmount
    Indicates the maximum bond value that has been formally approved or permitted for issuance or use in a given context.
  • E. maximumNumberOfHolders
    Indicates the greatest allowable or observed count of entities that can simultaneously hold or possess a given item, role, or resource.
  • F. None of above. chosen

Provenance (4 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_69eee9ba94bc8190b44c5d4397d04ecd completed April 27, 2026, 4:44 a.m.
NER Named-entity recognition batch_69f662a29b3881909957a7e3b986653c completed May 2, 2026, 8:46 p.m.
PD Predicate disambiguation batch_69f660eea4648190b0d5e24293607813 completed May 2, 2026, 8:39 p.m.
PDg Predicate description generation batch_69f661b47d088190934f63884a203261 completed May 2, 2026, 8:42 p.m.
Created at: April 27, 2026, 5:32 a.m.