Triple

T20217390
Position Surface form Disambiguated ID Type / Status
Subject Mary Lou's Mass E495162 entity
Predicate hasPart P35 FINISHED
Object Gloria
Gloria is a central liturgical hymn of praise in the Catholic Mass, traditionally sung or recited near the beginning of the service.
E54443 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: Gloria | Statement: [Mary Lou's Mass, hasPart, Gloria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gloria
Context triple: [Mary Lou's Mass, hasPart, Gloria]
  • A. Gloria
    "Gloria" is a 2019 folk-rock single by American band The Lumineers, known for its raw portrayal of addiction and family struggle.
  • B. Gloria
    Gloria is the friendly, strong-willed hippopotamus from the Madagascar animated film series who often teams up with King Julien and the other zoo animals.
  • C. Gloria
    Gloria is an American sitcom centered on Gloria Stivic, the daughter from "All in the Family," as she navigates life as a single mother.
  • D. Gloria
    "Gloria" is a classic 1964 rock song by Van Morrison, originally recorded with his band Them and later widely covered, known for its simple three-chord structure and iconic shouted chorus.
  • E. Gloria
    "Gloria" is a stage play by Branden Jacobs-Jenkins that satirically explores ambition, trauma, and media exploitation within the culture of a New York publishing office.
  • 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: Gloria
Triple: [Mary Lou's Mass, hasPart, Gloria]
Generated description
Gloria is a central liturgical hymn of praise in the Catholic Mass, traditionally sung or recited near the beginning of the service.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gloria
Target entity description: Gloria is a central liturgical hymn of praise in the Catholic Mass, traditionally sung or recited near the beginning of the service.
  • A. Gloria chosen
    Gloria is a joyful hymn of praise in Christian liturgy, traditionally sung during major celebrations such as the Easter Vigil.
  • B. Gloria
    Gloria is a fictional character featured in Green Day’s song “¡Viva La Gloria!” from their rock opera album 21st Century Breakdown.
  • C. Gloria
    Gloria is a feminine given name of Latin origin meaning "glory," borne by numerous notable figures in entertainment, politics, and literature.
  • D. Gloria
    "Gloria" is a classic 1964 rock song by Van Morrison, originally recorded with his band Them and later widely covered, known for its simple three-chord structure and iconic shouted chorus.
  • E. Gloria
    "Gloria" is a 2019 folk-rock single by American band The Lumineers, known for its raw portrayal of addiction and family struggle.
  • F. None of above.

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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66eda2f188190adf39d895e8b99f2 completed April 20, 2026, 6:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0843f6580c8190a615d79f15f8143d completed May 16, 2026, 10:16 a.m.
NEDg Description generation batch_6a08449001b4819089cd6399ad76fe49 completed May 16, 2026, 10:18 a.m.
NED2 Entity disambiguation (via description) batch_6a08452b6f9c8190bcaf705698b4a6d2 completed May 16, 2026, 10:21 a.m.
Created at: April 11, 2026, 11:39 p.m.