Triple
T26870818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Markopolos |
E676604
|
entity |
| Predicate | warnedRegulator |
P86402
|
FINISHED |
| Object | U.S. Securities and Exchange Commission |
—
|
NE NERFINISHED |
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: U.S. Securities and Exchange Commission | Statement: [Harry Markopolos, warnedRegulator, U.S. Securities and Exchange Commission]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: warnedRegulator Context triple: [Harry Markopolos, warnedRegulator, U.S. Securities and Exchange Commission]
-
A.
warnsAbout
Indicates that one entity alerts or cautions another entity about a potential danger, risk, or problem.
-
B.
warningIssued
Indicates that a formal warning or alert has been communicated from one entity to another regarding a potential or existing risk, problem, or violation.
-
C.
warningGivenBy
chosen
Indicates that one entity issues or delivers a warning to another entity.
-
D.
attemptedToRegulate
Indicates an entity made an effort or took action to impose rules, controls, or restrictions on another entity or activity, regardless of whether that effort succeeded.
-
E.
regulatorCovered
Indicates that an entity falls under the authority, oversight, or jurisdiction of a specified regulatory body.
- F. None of above.
Provenance (3 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_69f61e9b57bc8190a262eb0203f9dd3f |
completed | May 2, 2026, 3:56 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:32 a.m.