Triple

T10283819
Position Surface form Disambiguated ID Type / Status
Subject Frank Dobson E241174 entity
Predicate familyName P18 FINISHED
Object Dobson
Dobson is an English-language surname borne by various notable individuals across fields such as politics, sports, and the arts.
E852597 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: Dobson | Statement: [Frank Dobson, familyName, Dobson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dobson
Context triple: [Frank Dobson, familyName, Dobson]
  • A. Dobley
    Dobley is a significant urban center in Somalia's Jubaland region, serving as an important local hub for trade and administration.
  • B. Dobkin
    Dobkin is a Jewish surname borne by various notable individuals, including figures in Israeli politics, arts, and public life.
  • C. Michell
    Michell is a given name and surname that functions as a variant spelling of Mitchell.
  • D. Bonnell
    Bonnell is a former parliamentary constituency in the United Kingdom that was represented in the House of Commons before being succeeded by the Saltwell constituency.
  • E. Bonnell
    Bonnell is the microarchitecture that underpinned Intel's first-generation Atom processors, designed for low-power, energy-efficient computing in mobile and embedded devices.
  • 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: Dobson
Triple: [Frank Dobson, familyName, Dobson]
Generated description
Dobson is an English-language surname borne by various notable individuals across fields such as politics, sports, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dobson
Target entity description: Dobson is an English-language surname borne by various notable individuals across fields such as politics, sports, and the arts.
  • A. Dobley
    Dobley is a significant urban center in Somalia's Jubaland region, serving as an important local hub for trade and administration.
  • B. Dobkin
    Dobkin is a Jewish surname borne by various notable individuals, including figures in Israeli politics, arts, and public life.
  • C. Michell
    Michell is a given name and surname that functions as a variant spelling of Mitchell.
  • D. Bonnell
    Bonnell is a former parliamentary constituency in the United Kingdom that was represented in the House of Commons before being succeeded by the Saltwell constituency.
  • E. Bonnell
    Bonnell is the microarchitecture that underpinned Intel's first-generation Atom processors, designed for low-power, energy-efficient computing in mobile and embedded devices.
  • 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_69d381aaafc08190af475ef58dc16aba completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2b5853081909cd0397e08a0f44d completed April 7, 2026, 9:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f83c3c488190b728783bc260b006 completed April 9, 2026, 12:52 a.m.
NEDg Description generation batch_69d6fcae243c819095a2e791716805bd completed April 9, 2026, 1:11 a.m.
NED2 Entity disambiguation (via description) batch_69d6fd3495fc8190a093d2536cfbe58a completed April 9, 2026, 1:13 a.m.
Created at: April 6, 2026, 11:39 a.m.