Triple
T20410179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lighthouse Family |
E500567
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
High
"High" is a mellow, uplifting pop-soul song by the British duo Lighthouse Family, known for its smooth vocals and optimistic, radio-friendly sound.
|
E1429610
|
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: High | Statement: [Lighthouse Family, notableWork, High]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: High Context triple: [Lighthouse Family, notableWork, High]
-
A.
High
"High" is a song by British singer-songwriter James Blunt from his debut album "Back to Bedlam."
-
B.
High
"High" is a 2018 electropop single by American DJ duo The Chainsmokers, known for its catchy melody and introspective lyrics about a turbulent relationship.
-
C.
High
"High" is a popular Afrobeats song by Nigerian singer Adekunle Gold, known for its upbeat production and collaboration with Davido.
-
D.
HighC
HighC is a computer-assisted music composition system known for its graphical, intuitive interface that lets users draw and manipulate sound directly.
-
E.
Hight
Hight is a music producer and DJ known for collaborating with artists in the electronic and dance-pop scene, including German DJ Felix Jaehn.
- 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: High Triple: [Lighthouse Family, notableWork, High]
Generated description
"High" is a mellow, uplifting pop-soul song by the British duo Lighthouse Family, known for its smooth vocals and optimistic, radio-friendly sound.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: High Target entity description: "High" is a mellow, uplifting pop-soul song by the British duo Lighthouse Family, known for its smooth vocals and optimistic, radio-friendly sound.
-
A.
High
"High" is a song by British singer-songwriter James Blunt from his debut album "Back to Bedlam."
-
B.
High
"High" is a 2018 electropop single by American DJ duo The Chainsmokers, known for its catchy melody and introspective lyrics about a turbulent relationship.
-
C.
High
"High" is a popular Afrobeats song by Nigerian singer Adekunle Gold, known for its upbeat production and collaboration with Davido.
-
D.
HighC
HighC is a computer-assisted music composition system known for its graphical, intuitive interface that lets users draw and manipulate sound directly.
-
E.
Hight
Hight is a music producer and DJ known for collaborating with artists in the electronic and dance-pop scene, including German DJ Felix Jaehn.
- 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_69e0b4a935588190b9446a99b37ced44 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67a3ecb348190ae777f6276037828 |
completed | April 20, 2026, 7:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a087b21cb308190a9313a24a902b44d |
completed | May 16, 2026, 2:11 p.m. |
| NEDg | Description generation | batch_6a088015c514819087967845614dd25d |
completed | May 16, 2026, 2:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0880b79edc81908b180db5338f57db |
completed | May 16, 2026, 2:35 p.m. |
Created at: April 16, 2026, 11:29 a.m.