Triple

T1207286
Position Surface form Disambiguated ID Type / Status
Subject GPO E25917 entity
Predicate product P490 FINISHED
Object Congressional Record E1631 NE 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: Congressional Record | Statement: [GPO, product, Congressional Record]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Congressional Record
Context triple: [GPO, product, Congressional Record]
  • A. Congressional Record chosen
    The Congressional Record is the official, substantially verbatim transcript of the debates, proceedings, and activities of the United States Congress.
  • B. House Journal
    House Journal is the official published record of the proceedings and actions of the Massachusetts House of Representatives.
  • C. United States Statutes at Large
    The United States Statutes at Large is the official chronological compilation of all laws and resolutions enacted by the U.S. Congress.
  • D. Hansard
    Hansard is the official verbatim record of debates and proceedings in the UK Parliament.
  • E. Senate Journal
    The Senate Journal is the official record of proceedings and actions taken by the Massachusetts Senate.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69a4942b30f08190a91c60573e16b5ef completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bdc483b481908e5bfef5d2f4fc5a completed March 1, 2026, 10:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac7f3f4c508190bdc3d436d393daf9 completed March 7, 2026, 7:40 p.m.
Created at: March 1, 2026, 7:46 p.m.