Triple

T2340833
Position Surface form Disambiguated ID Type / Status
Subject Eric Holder E45021 entity
Predicate familyName P18 FINISHED
Object Holder
Holder is a surname most prominently associated with Eric Holder, the first African American U.S. Attorney General.
E259187 NE FINISHED

How this triple was built (4 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: Holder | Statement: [Eric Holder, familyName, Holder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Holder
Context triple: [Eric Holder, familyName, Holder]
  • A. Carrier
    Carrier is a leading global brand specializing in heating, ventilation, air conditioning (HVAC), and refrigeration solutions.
  • B. Hart
    Hart is a surname most famously associated with Moss Hart, the acclaimed American playwright and theater director known for works like "You Can't Take It with You" and "Once in a Lifetime."
  • C. The Box
    The Box is an informal nickname for the TARDIS, the Doctor’s iconic time-traveling spaceship and time machine from the British science fiction series Doctor Who.
  • D. Selloi
    The Selloi were the ancient priests associated with the oracle of Zeus at Dodona in Epirus, known from Homeric tradition.
  • E. The Mister
    The Mister is a contemporary romance novel by E. L. James, known for its Cinderella-style love story and for being her follow-up to the Fifty Shades series.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Holder
Triple: [Eric Holder, familyName, Holder]
Generated description
Holder is a surname most prominently associated with Eric Holder, the first African American U.S. Attorney General.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Holder
Target entity description: Holder is a surname most prominently associated with Eric Holder, the first African American U.S. Attorney General.
  • A. Carrier
    Carrier is a leading global brand specializing in heating, ventilation, air conditioning (HVAC), and refrigeration solutions.
  • B. Hart
    Hart is a surname most famously associated with Moss Hart, the acclaimed American playwright and theater director known for works like "You Can't Take It with You" and "Once in a Lifetime."
  • C. The Box
    The Box is an informal nickname for the TARDIS, the Doctor’s iconic time-traveling spaceship and time machine from the British science fiction series Doctor Who.
  • D. Selloi
    The Selloi were the ancient priests associated with the oracle of Zeus at Dodona in Epirus, known from Homeric tradition.
  • E. Gardez
    Gardez is a city in eastern Afghanistan that serves as the capital of Paktia Province and an important regional administrative and commercial center.
  • F. None of above. chosen

Provenance (5 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_69a88917935081909b755dbf38e81024 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abc6abf1688190b7c404de0979149a completed March 7, 2026, 6:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae961fd8748190a82ca4c4b840d9f6 completed March 9, 2026, 9:42 a.m.
NEDg Description generation batch_69ae980425b0819092477f5cf9816d65 completed March 9, 2026, 9:51 a.m.
NED2 Entity disambiguation (via description) batch_69ae9bef58f881908161d143369ba11a completed March 9, 2026, 10:07 a.m.
Created at: March 4, 2026, 7:52 p.m.