Triple

T25014432
Position Surface form Disambiguated ID Type / Status
Subject Nancy Wyman E626086 entity
Predicate precededBy (Connecticut Comptroller) P159406 FINISHED
Object Edward Caldwell
Edward Caldwell is an American politician who served as Connecticut State Comptroller immediately before Nancy Wyman.
 E1694477 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: Edward Caldwell | Statement: [Nancy Wyman, precededBy (Connecticut Comptroller), Edward Caldwell]
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: Edward Caldwell
Triple: [Nancy Wyman, precededBy (Connecticut Comptroller), Edward Caldwell]
Generated description
Edward Caldwell is an American politician who served as Connecticut State Comptroller immediately before Nancy Wyman.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: precededBy (Connecticut Comptroller)
Context triple: [Nancy Wyman, precededBy (Connecticut Comptroller), Edward Caldwell]
  • A. precededBy (Governor of New York)
    Indicates that one entity held the position of Governor of New York before another entity.
  • B. precededBy (Governor of Vermont)
    Indicates that one holder of the office of Governor of Vermont served in that position before another specified holder.
  • C. precededBy (Governor of Maine)
    Indicates that one entity held the position of Governor of Maine before another entity.
  • D. precededBy (Governor of California)
    Indicates that one entity held the position of Governor of California before another entity in temporal order.
  • E. precededBy (Mayor of New York City)
    Indicates that one mayor of New York City held office before another mayor of New York City in chronological order.
  • 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_69e2ff27755881908490178e83701160 completed April 18, 2026, 3:48 a.m.
NER Named-entity recognition batch_69f584f07b648190aee894c1d5320bc3 completed May 2, 2026, 5 a.m.
NED1 Entity disambiguation (via context triple) batch_6a10cbc2a74481909c1e1a51e33ba3b0 completed May 22, 2026, 9:33 p.m.
NEDg Description generation batch_6a10cde4cc7c819082eea238a1e4a786 completed May 22, 2026, 9:43 p.m.
NED2 Entity disambiguation (via description) batch_6a10ce89ce6481908d758175a37488b8 completed May 22, 2026, 9:45 p.m.
PD Predicate disambiguation batch_69f4a0edd10c81908a052ab864d57c54 completed May 1, 2026, 12:47 p.m.
PDg Predicate description generation batch_69f55e497fa081909bc59a7b92c5df59 completed May 2, 2026, 2:15 a.m.
Created at: April 18, 2026, 6:06 a.m.