Triple

T9222901
Position Surface form Disambiguated ID Type / Status
Subject Felix Grundy E221606 entity
Predicate familyName P18 FINISHED
Object Grundy
Grundy is a surname of English origin borne by various notable individuals across politics, sports, and entertainment.
 E784946 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: Grundy | Statement: [Felix Grundy, familyName, Grundy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Grundy
Context triple: [Felix Grundy, familyName, Grundy]
  • A. Grund
    Grund is a historic, picturesque quarter of Luxembourg City known for its riverside setting, old architecture, and vibrant nightlife.
  • B. Kierling
    Kierling is a small locality in Lower Austria best known as the place where writer Franz Kafka spent his final days and died.
  • C. Bron
    Bron is a suburban commune in eastern France that forms part of the metropolitan area of Lyon.
  • D. Rollag
    Rollag is a small rural municipality in southeastern Norway known for its traditional wooden architecture and scenic valley landscapes.
  • E. Boerne
    Boerne is a small, historic town in south-central Texas known for its German heritage, charming downtown, and scenic Hill Country surroundings.
  • 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: Grundy
Triple: [Felix Grundy, familyName, Grundy]
Generated description
Grundy is a surname of English origin borne by various notable individuals across politics, sports, and entertainment.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Grundy
Target entity description: Grundy is a surname of English origin borne by various notable individuals across politics, sports, and entertainment.
  • A. Grund
    Grund is a historic, picturesque quarter of Luxembourg City known for its riverside setting, old architecture, and vibrant nightlife.
  • B. Kierling
    Kierling is a small locality in Lower Austria best known as the place where writer Franz Kafka spent his final days and died.
  • C. Bron
    Bron is a suburban commune in eastern France that forms part of the metropolitan area of Lyon.
  • D. Rollag
    Rollag is a small rural municipality in southeastern Norway known for its traditional wooden architecture and scenic valley landscapes.
  • E. Boerne
    Boerne is a small, historic town in south-central Texas known for its German heritage, charming downtown, and scenic Hill Country surroundings.
  • 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_69ca83ec8db08190a9110df8232885d2 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccda7903208190b4e29a1591aab78a completed April 1, 2026, 8:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0664565748190a45cf382fca72cbe completed April 4, 2026, 1:15 a.m.
NEDg Description generation batch_69d06771ba808190a7b10f664425e76e completed April 4, 2026, 1:20 a.m.
NED2 Entity disambiguation (via description) batch_69d068087ab881908edcfd384a2e3f07 completed April 4, 2026, 1:23 a.m.
Created at: March 30, 2026, 7:28 p.m.