Triple

T28717825
Position Surface form Disambiguated ID Type / Status
Subject FBI Top Echelon Informant Program E730009 entity
Predicate notableFBIHandler P203387 FINISHED
Object John J. Connolly Jr.
John J. Connolly Jr. is a former FBI agent best known for his corrupt relationship with Boston mob boss Whitey Bulger, which led to his conviction for racketeering and other crimes.
 E1834699 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: John J. Connolly Jr. | Statement: [FBI Top Echelon Informant Program, notableFBIHandler, John J. Connolly Jr.]
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: John J. Connolly Jr.
Triple: [FBI Top Echelon Informant Program, notableFBIHandler, John J. Connolly Jr.]
Generated description
John J. Connolly Jr. is a former FBI agent best known for his corrupt relationship with Boston mob boss Whitey Bulger, which led to his conviction for racketeering and other crimes.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: notableFBIHandler
Context triple: [FBI Top Echelon Informant Program, notableFBIHandler, John J. Connolly Jr.]
  • A. FBIConclusion
    Indicates that the FBI has reached an official finding or determination about a case, event, or subject.
  • B. primaryContactAtFBI
    Indicates that one entity serves as the main point of contact for another entity within the FBI.
  • C. providesToFBI
    Indicates that one entity supplies or delivers information, resources, or assistance to the FBI.
  • D. FBIStatus
    Indicates the relationship of an entity to the FBI, such as its status, classification, or involvement in FBI records or activities.
  • E. notableProsecutor
    Indicates that the person served as a prosecutor in a way that is widely recognized as significant or noteworthy.
  • F. None of above. chosen

Provenance (7 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_69f043e7d5a4819094b18aca10b1e024 completed April 28, 2026, 5:21 a.m.
NER Named-entity recognition batch_6a0174142430819084aa1235500b9d3b completed May 11, 2026, 6:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a24a24ce9008190a4bada87fd8221d5 completed June 6, 2026, 10:42 p.m.
NEDg Description generation batch_6a24a638e30881908d94bc85bfb4b3a4 completed June 6, 2026, 10:59 p.m.
NED2 Entity disambiguation (via description) batch_6a24b191b75c8190842a72cd498304fe completed June 6, 2026, 11:47 p.m.
PD Predicate disambiguation batch_6a0171a6e0088190958679bb6cb24a70 completed May 11, 2026, 6:05 a.m.
PDg Predicate description generation batch_6a0174134f688190861a1acedc9ea060 completed May 11, 2026, 6:15 a.m.
Created at: April 28, 2026, 5:51 a.m.