Triple

T17041002
Position Surface form Disambiguated ID Type / Status
Subject Geoffrey Pullum E413445 entity
Predicate familyName P18 FINISHED
Object Pullum
Pullum is the surname of Geoffrey Pullum, a prominent linguist known for his work on English grammar and his co-authorship of *The Cambridge Grammar of the English Language*.
E1247514 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: Pullum | Statement: [Geoffrey Pullum, familyName, Pullum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pullum
Context triple: [Geoffrey Pullum, familyName, Pullum]
  • A. Paama
    Paama is an Oceanic language spoken primarily on Paama Island in central Vanuatu.
  • B. Palilula
    Palilula is one of the urban municipalities of Belgrade, Serbia, encompassing both central city neighborhoods and outlying suburban and rural areas.
  • C. Putidamo
    Putidamo is the Chinese name for Bodhidharma, the semi-legendary Buddhist monk credited with transmitting Chan (Zen) Buddhism to China.
  • D. The Lenny
    The Lenny is a track featured in the Balf Quarry racing environment, known for its challenging layout and integration into the quarry-themed course.
  • E. Palookas
    "Palookas" is a track from Talib Kweli's album "Gutter Rainbows," showcasing his lyrically driven, socially conscious hip-hop style.
  • 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: Pullum
Triple: [Geoffrey Pullum, familyName, Pullum]
Generated description
Pullum is the surname of Geoffrey Pullum, a prominent linguist known for his work on English grammar and his co-authorship of *The Cambridge Grammar of the English Language*.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pullum
Target entity description: Pullum is the surname of Geoffrey Pullum, a prominent linguist known for his work on English grammar and his co-authorship of *The Cambridge Grammar of the English Language*.
  • A. Paama
    Paama is an Oceanic language spoken primarily on Paama Island in central Vanuatu.
  • B. Palilula
    Palilula is one of the urban municipalities of Belgrade, Serbia, encompassing both central city neighborhoods and outlying suburban and rural areas.
  • C. Putidamo
    Putidamo is the Chinese name for Bodhidharma, the semi-legendary Buddhist monk credited with transmitting Chan (Zen) Buddhism to China.
  • D. The Lenny
    The Lenny is a track featured in the Balf Quarry racing environment, known for its challenging layout and integration into the quarry-themed course.
  • E. Palookas
    "Palookas" is a track from Talib Kweli's album "Gutter Rainbows," showcasing his lyrically driven, socially conscious hip-hop style.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d8f6a0c08190a838279b83b55b72 completed April 18, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012338a95c8190951db96209edb61a completed May 11, 2026, 12:30 a.m.
NEDg Description generation batch_6a01241510048190ae1c459873f8a587 completed May 11, 2026, 12:34 a.m.
NED2 Entity disambiguation (via description) batch_6a0124e389908190b2ee3121be2c9383 completed May 11, 2026, 12:37 a.m.
Created at: April 10, 2026, 5:33 a.m.