Triple

T10104030
Position Surface form Disambiguated ID Type / Status
Subject Boygenius (EP) E216272 entity
Predicate hasPart P35 FINISHED
Object “Salt in the Wound”
“Salt in the Wound” is a song by the indie rock supergroup boygenius, featured on their self-titled debut EP.
 E840668 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: “Salt in the Wound” | Statement: [Boygenius (EP), hasPart, “Salt in the Wound”]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: “Salt in the Wound”
Context triple: [Boygenius (EP), hasPart, “Salt in the Wound”]
  • A. “Widow’s Walk”
    “Widow’s Walk” is a song that forms one of the individual pieces within the larger musical work titled *Song Cycle*.
  • B. Wounds in the Rain
    Wounds in the Rain is a collection of short stories by American author Stephen Crane, largely inspired by his experiences as a war correspondent during the Spanish–American War.
  • C. "Pain"
    "Pain" is a song by American singer-songwriter Muni Long, known for its emotive lyrics and R&B-influenced sound.
  • D. Old Wounds
    "Old Wounds" is an episode of the animated TV series "Teen Titans" that introduces the character Isaac.
  • E. Old Wounds
    "Old Wounds" is the pilot episode of the science fiction comedy-drama series *The Orville*, which introduces the main characters and the show's spacefaring setting.
  • 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: “Salt in the Wound”
Triple: [Boygenius (EP), hasPart, “Salt in the Wound”]
Generated description
“Salt in the Wound” is a song by the indie rock supergroup boygenius, featured on their self-titled debut EP.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: “Salt in the Wound”
Target entity description: “Salt in the Wound” is a song by the indie rock supergroup boygenius, featured on their self-titled debut EP.
  • A. “Widow’s Walk”
    “Widow’s Walk” is a song that forms one of the individual pieces within the larger musical work titled *Song Cycle*.
  • B. Wounds in the Rain
    Wounds in the Rain is a collection of short stories by American author Stephen Crane, largely inspired by his experiences as a war correspondent during the Spanish–American War.
  • C. "Pain"
    "Pain" is a song by American singer-songwriter Muni Long, known for its emotive lyrics and R&B-influenced sound.
  • D. Old Wounds
    "Old Wounds" is an episode of the animated TV series "Teen Titans" that introduces the character Isaac.
  • E. Old Wounds
    "Old Wounds" is the pilot episode of the science fiction comedy-drama series *The Orville*, which introduces the main characters and the show's spacefaring setting.
  • 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_69ca83d039f08190b9d10363221c69fb completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd09c961081909848acec4438c300 completed April 2, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b6dcca848190851f6f1968fe244c completed April 5, 2026, 7:24 p.m.
NEDg Description generation batch_69d2b7e64fcc8190805a6a31c8a3786f completed April 5, 2026, 7:28 p.m.
NED2 Entity disambiguation (via description) batch_69d2b883959481909f330a26863621ae completed April 5, 2026, 7:31 p.m.
Created at: March 30, 2026, 9:03 p.m.