Triple

T19109987
Position Surface form Disambiguated ID Type / Status
Subject University of Oxford Gardens, Libraries and Museums E467760 entity
Predicate shortName P43 FINISHED
Object GLAM
GLAM is the collective name for the University of Oxford’s network of gardens, libraries, and museums that steward and showcase its cultural and scientific collections.
 E1358857 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: GLAM | Statement: [University of Oxford Gardens, Libraries and Museums, shortName, GLAM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GLAM
Context triple: [University of Oxford Gardens, Libraries and Museums, shortName, GLAM]
  • A. Glam
    "Glam" is a track from Christina Aguilera's album *Bionic*, known for its fashion-themed lyrics and electro-pop production.
  • B. Glamour
    Glamour is a popular international women's magazine known for its coverage of fashion, beauty, lifestyle, and celebrity culture.
  • C. Glam Slam
    "Glam Slam" is a funk-infused pop song by Prince, released in 1988 as a single from his album Lovesexy.
  • D. Glitz
    Glitz is a crime novel by Elmore Leonard that follows a tough Miami cop entangled with a vengeful ex-con and the seedy underworld of Atlantic City.
  • E. 88Glam
    88Glam is a Canadian hip hop duo known for their atmospheric trap sound and collaborations within Toronto’s rap scene.
  • 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: GLAM
Triple: [University of Oxford Gardens, Libraries and Museums, shortName, GLAM]
Generated description
GLAM is the collective name for the University of Oxford’s network of gardens, libraries, and museums that steward and showcase its cultural and scientific collections.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GLAM
Target entity description: GLAM is the collective name for the University of Oxford’s network of gardens, libraries, and museums that steward and showcase its cultural and scientific collections.
  • A. Glam
    "Glam" is a track from Christina Aguilera's album *Bionic*, known for its fashion-themed lyrics and electro-pop production.
  • B. Glamour
    Glamour is a popular international women's magazine known for its coverage of fashion, beauty, lifestyle, and celebrity culture.
  • C. Glam Slam
    "Glam Slam" is a funk-infused pop song by Prince, released in 1988 as a single from his album Lovesexy.
  • D. Glitz
    Glitz is a crime novel by Elmore Leonard that follows a tough Miami cop entangled with a vengeful ex-con and the seedy underworld of Atlantic City.
  • E. 88Glam
    88Glam is a Canadian hip hop duo known for their atmospheric trap sound and collaborations within Toronto’s rap scene.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e392ef488190a230b1d2890b2a9d completed April 20, 2026, 8:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05dda4d5c881909162a8c331bb3c95 completed May 14, 2026, 2:35 p.m.
NEDg Description generation batch_6a05dfd00d1081908086212708501c8f completed May 14, 2026, 2:44 p.m.
NED2 Entity disambiguation (via description) batch_6a05e0f25e2481909ddd3f2181b784ea completed May 14, 2026, 2:49 p.m.
Created at: April 10, 2026, 12:04 p.m.