Triple

T4825358
Position Surface form Disambiguated ID Type / Status
Subject Marshall University E107809 entity
Predicate hasLibrary P35 FINISHED
Object Drinko Library
Drinko Library is the main academic library at Marshall University, serving as a central hub for research, study, and information resources for students and faculty.
E473397 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: Drinko Library | Statement: [Marshall University, hasLibrary, Drinko Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Drinko Library
Context triple: [Marshall University, hasLibrary, Drinko Library]
  • A. Five Drinks Ago
    Five Drinks Ago is a song featured on the album "Heartland."
  • B. Pym Tasting Lab
    Pym Tasting Lab is a Marvel-themed eatery and bar in Disney’s Avengers Campus that playfully uses “Pym Particle” science to serve creatively sized snacks and beverages.
  • C. Liquor Locker
    "Liquor Locker" is a song by American rapper Vic Mensa that showcases his melodic style and introspective lyricism.
  • D. Ruffle Bar
    Ruffle Bar is an uninhabited island in Jamaica Bay, New York City, known for its salt marshes, bird habitat, and remnants of a former small community.
  • E. Drink a Beer
    "Drink a Beer" is a reflective country ballad by Luke Bryan that poignantly addresses loss and remembrance.
  • 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: Drinko Library
Triple: [Marshall University, hasLibrary, Drinko Library]
Generated description
Drinko Library is the main academic library at Marshall University, serving as a central hub for research, study, and information resources for students and faculty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Drinko Library
Target entity description: Drinko Library is the main academic library at Marshall University, serving as a central hub for research, study, and information resources for students and faculty.
  • A. Five Drinks Ago
    Five Drinks Ago is a song featured on the album "Heartland."
  • B. Pym Tasting Lab
    Pym Tasting Lab is a Marvel-themed eatery and bar in Disney’s Avengers Campus that playfully uses “Pym Particle” science to serve creatively sized snacks and beverages.
  • C. Liquor Locker
    "Liquor Locker" is a song by American rapper Vic Mensa that showcases his melodic style and introspective lyricism.
  • D. Ruffle Bar
    Ruffle Bar is an uninhabited island in Jamaica Bay, New York City, known for its salt marshes, bird habitat, and remnants of a former small community.
  • E. Drink a Beer
    "Drink a Beer" is a reflective country ballad by Luke Bryan that poignantly addresses loss and remembrance.
  • 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_69bd43fac8188190803f0327190621e4 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6cadb2bc81909455149e46eb593a completed March 20, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4dca2b708190ac05c91ba04d9ff6 completed March 21, 2026, 7:50 a.m.
NEDg Description generation batch_69be4fc6ea3c819099ede84700eb5a5a completed March 21, 2026, 7:59 a.m.
NED2 Entity disambiguation (via description) batch_69be5146f1ac8190977512323af69487 completed March 21, 2026, 8:05 a.m.
Created at: March 20, 2026, 1:24 p.m.