Triple

T15632829
Position Surface form Disambiguated ID Type / Status
Subject Tommy Carcetti E375860 entity
Predicate campaignsForOffice P75922 FINISHED
Object Mayor of Baltimore 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: Mayor of Baltimore | Statement: [Tommy Carcetti, campaignsForOffice, Mayor of Baltimore]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: campaignsForOffice
Context triple: [Tommy Carcetti, campaignsForOffice, Mayor of Baltimore]
  • A. campaignForOffice chosen
    Indicates that an individual is actively seeking election to a public office or position through an organized political campaign.
  • B. campaigns
    Indicates that an entity actively conducts or participates in an organized effort or series of actions aimed at achieving a specific goal, often in political, marketing, or advocacy contexts.
  • C. nominatedForOffice
    Indicates that an entity has been formally put forward as a candidate to hold a particular office or position.
  • D. electionForOffice
    Indicates that an election event is held to select or fill a specific office or position.
  • E. campaignFinanceContext
    Indicates the relationship in which an action, event, or statement occurs within the specific circumstances, rules, or issues related to campaign financing.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eb7338881909f3c430bb73f91d1 completed April 16, 2026, 2:51 a.m.
PD Predicate disambiguation batch_69deda868d4481908f4bce1c64d2902a completed April 15, 2026, 12:23 a.m.
Created at: April 10, 2026, 4:14 a.m.