Triple
T19566131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Where the Light Goes |
E489586
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object |
Hang on Every Word
"Hang on Every Word" is a song by American pop rock band Matchbox Twenty from their 2023 album "Where the Light Goes."
|
E1383548
|
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: Hang on Every Word | Statement: [Where the Light Goes, hasTrack, Hang on Every Word]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hang on Every Word Context triple: [Where the Light Goes, hasTrack, Hang on Every Word]
-
A.
Hang On to Yourself
"Hang On to Yourself" is a high-energy glam rock song by David Bowie, known for its driving rhythm and role in the Ziggy Stardust concept narrative.
-
B.
Holding On
"Holding On" is a song featured on Jay Sean's debut studio album "Me Against Myself."
-
C.
Holding On
"Holding On" is a song by the British electronic music duo Disclosure, known for its soulful vocals and house-influenced production.
-
D.
Holding On
"Holding On" is a soulful jazz and R&B song by Gregory Porter, known for its rich vocals and emotive, socially conscious lyrics.
-
E.
Hang-On
Hang-On is a classic arcade-style motorcycle racing video game developed by Sega and designed by Yu Suzuki, known for pioneering realistic bike-racing gameplay in the mid-1980s.
- 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: Hang on Every Word Triple: [Where the Light Goes, hasTrack, Hang on Every Word]
Generated description
"Hang on Every Word" is a song by American pop rock band Matchbox Twenty from their 2023 album "Where the Light Goes."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hang on Every Word Target entity description: "Hang on Every Word" is a song by American pop rock band Matchbox Twenty from their 2023 album "Where the Light Goes."
-
A.
Hang On to Yourself
"Hang On to Yourself" is a high-energy glam rock song by David Bowie, known for its driving rhythm and role in the Ziggy Stardust concept narrative.
-
B.
Holding On
"Holding On" is a song featured on Jay Sean's debut studio album "Me Against Myself."
-
C.
Holding On
"Holding On" is a song by the British electronic music duo Disclosure, known for its soulful vocals and house-influenced production.
-
D.
Holding On
"Holding On" is a soulful jazz and R&B song by Gregory Porter, known for its rich vocals and emotive, socially conscious lyrics.
-
E.
Hang-On
Hang-On is a classic arcade-style motorcycle racing video game developed by Sega and designed by Yu Suzuki, known for pioneering realistic bike-racing gameplay in the mid-1980s.
- 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63f777cf081909312b46ac09bce7c |
completed | April 20, 2026, 3 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0757898214819090d82acf3fd830ff |
completed | May 15, 2026, 5:27 p.m. |
| NEDg | Description generation | batch_6a075865eaac819085b35d165fda91d4 |
completed | May 15, 2026, 5:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07590b84488190a33889335ba95c95 |
completed | May 15, 2026, 5:34 p.m. |
Created at: April 10, 2026, 1:42 p.m.