Triple

T3128724
Position Surface form Disambiguated ID Type / Status
Subject Blood Bank E65358 entity
Predicate hasTrack P3284 FINISHED
Object Blood Bank (song)
"Blood Bank" is an indie folk song by Bon Iver, noted for its atmospheric production and introspective lyrics, and serves as the title track of the band's 2009 EP.
 E329889 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: Blood Bank (song) | Statement: [Blood Bank, hasTrack, Blood Bank (song)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Blood Bank (song)
Context triple: [Blood Bank, hasTrack, Blood Bank (song)]
  • A. Young Blood
    "Young Blood" is a classic rhythm and blues song from the 1950s, best known in its hit version by The Coasters and widely covered in rock and roll history.
  • B. Bloods
    Bloods is a popular nickname for the Sydney Swans, an Australian Football League club known for its red-and-white colors and strong team culture.
  • C. A Song
    "A Song" is a track by Greek composer Vangelis featured on his 1979 electronic music album "Earth."
  • D. Bloodflow
    "Bloodflow" is a song by the experimental pop band Dongs of Sevotion.
  • E. Bleed for This
    Bleed for This is a 2016 biographical sports drama film about boxer Vinny Pazienza’s remarkable comeback after a near-fatal car accident.
  • 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: Blood Bank (song)
Triple: [Blood Bank, hasTrack, Blood Bank (song)]
Generated description
"Blood Bank" is an indie folk song by Bon Iver, noted for its atmospheric production and introspective lyrics, and serves as the title track of the band's 2009 EP.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Blood Bank (song)
Target entity description: "Blood Bank" is an indie folk song by Bon Iver, noted for its atmospheric production and introspective lyrics, and serves as the title track of the band's 2009 EP.
  • A. Young Blood
    "Young Blood" is a classic rhythm and blues song from the 1950s, best known in its hit version by The Coasters and widely covered in rock and roll history.
  • B. Bloods
    Bloods is a popular nickname for the Sydney Swans, an Australian Football League club known for its red-and-white colors and strong team culture.
  • C. A Song
    "A Song" is a track by Greek composer Vangelis featured on his 1979 electronic music album "Earth."
  • D. Bloodflow
    "Bloodflow" is a song by the experimental pop band Dongs of Sevotion.
  • E. Bleed for This
    Bleed for This is a 2016 biographical sports drama film about boxer Vinny Pazienza’s remarkable comeback after a near-fatal car accident.
  • 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_69ad8580c72481909672d37acf647893 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada548123c8190bcfe780c65941585 completed March 8, 2026, 4:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69b20f7c70108190b61177d1581fc33f completed March 12, 2026, 12:57 a.m.
NEDg Description generation batch_69b2138e2bdc8190aa0a8a1dcd1e20fc completed March 12, 2026, 1:14 a.m.
NED2 Entity disambiguation (via description) batch_69b21438b6e881908da0117ebc9bb2b4 completed March 12, 2026, 1:17 a.m.
Created at: March 8, 2026, 3:04 p.m.