Triple
T14081413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theory of a Deadman |
E338877
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Angel
"Angel" is a rock ballad by Canadian band Theory of a Deadman, known for its emotional lyrics and melodic, radio-friendly sound.
|
E1077724
|
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: Angel | Statement: [Theory of a Deadman, notableWork, Angel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angel Context triple: [Theory of a Deadman, notableWork, Angel]
-
A.
Angel
Angel is a given name used across various cultures, often associated with spiritual or celestial connotations.
-
B.
Angel
An angel is a spiritual being found in various religious traditions, typically depicted as a messenger or servant of the divine.
-
C.
Angel
Angel is a winged mutant warrior in the X-Men universe, often depicted with metallic feathered wings and a conflicted, tormented nature.
-
D.
Angel
Angel is a character in William Wordsworth's autobiographical poem "The Prelude," symbolizing spiritual guidance and inspiration in the poet's inner and artistic development.
-
E.
Angel
Angel is a fictional character who is part of the Whole Sick Crew in Thomas Pynchon's novel "V."
- 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: Angel Triple: [Theory of a Deadman, notableWork, Angel]
Generated description
"Angel" is a rock ballad by Canadian band Theory of a Deadman, known for its emotional lyrics and melodic, radio-friendly sound.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Angel Target entity description: "Angel" is a rock ballad by Canadian band Theory of a Deadman, known for its emotional lyrics and melodic, radio-friendly sound.
-
A.
Angel
"Angel" is a song by the American rock band Aerosmith, best known as a power ballad from their 1987 album *Permanent Vacation*.
-
B.
Angel
"Angel" is a melancholic, piano-driven ballad by Canadian singer-songwriter Sarah McLachlan, widely known for its emotional resonance and use in various charitable and memorial contexts.
-
C.
Angel
"Angel" is a dark, trip hop song by Massive Attack, known for its brooding atmosphere, slow-building intensity, and prominent use in film and television soundtracks.
-
D.
Angel
"Angel" is a romantic reggae fusion song by Shaggy, featuring Rayvon, best known for its smooth melody and chart-topping success in the early 2000s.
-
E.
Angel
"Angel" is a 1984 pop song by Madonna, released as a single from her album "Like a Virgin."
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5f759c81909bfd60ab35b0937b |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb6673de881909653c7691422b800 |
completed | May 7, 2026, 3:57 p.m. |
| NEDg | Description generation | batch_69fcc3b8aea881909b11a4671314810e |
completed | May 7, 2026, 4:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fcc450fea881909e3b5bbd96469a8b |
completed | May 7, 2026, 4:56 p.m. |
Created at: April 9, 2026, 10:21 p.m.