Triple

T33926638
Position Surface form Disambiguated ID Type / Status
Subject Special Prosecutor E869769 entity
Predicate subsequentOfficeholder P33240 FINISHED
Object Henry Ruth (acting)
Henry Ruth was an American lawyer who served as acting Special Prosecutor during the Watergate investigation following Archibald Cox’s dismissal.
 E2073684 NE FINISHED

How this triple was built (3 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: Henry Ruth (acting) | Statement: [Special Prosecutor, subsequentOfficeholder, Henry Ruth (acting)]
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: Henry Ruth (acting)
Triple: [Special Prosecutor, subsequentOfficeholder, Henry Ruth (acting)]
Generated description
Henry Ruth was an American lawyer who served as acting Special Prosecutor during the Watergate investigation following Archibald Cox’s dismissal.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: subsequentOfficeholder
Context triple: [Special Prosecutor, subsequentOfficeholder, Henry Ruth (acting)]
  • A. successorOfficeHolder chosen
    Indicates that one office holder directly follows another in occupying the same official position.
  • B. lastOfficeHolderLaterBecame
    Indicates that the person who most recently held a given office subsequently went on to hold another specified office or role.
  • C. namedAfterOfficeholder
    Indicates that one entity is named in honor of, or derived from the name of, a person who has held a particular public or official office.
  • D. successorOfficeTo
    Indicates that one office or position directly follows and replaces another in an official sequence or hierarchy.
  • E. subsequentHeadOfGovernment
    Indicates that one entity served as the next head of government following another entity in an official succession.
  • F. None of above.

Provenance (6 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_69f349992c508190aa4afa24a086cc8c completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f7064e906881909c3186c646145d34 completed May 3, 2026, 8:24 a.m.
NED1 Entity disambiguation (via context triple) batch_6a36825668f48190bb8b1ce35ee5eac4 completed June 20, 2026, 12:06 p.m.
NEDg Description generation batch_6a3683c4bc048190b1ec64377130d76c completed June 20, 2026, 12:12 p.m.
NED2 Entity disambiguation (via description) batch_6a36848248c081909b5ab57a8c3accc6 completed June 20, 2026, 12:16 p.m.
PD Predicate disambiguation batch_69f70100ec1c8190a6b97f50e88891f2 completed May 3, 2026, 8:02 a.m.
Created at: May 1, 2026, 1:49 a.m.