Triple
T9305721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocky Mountain High |
E223879
|
entity |
| Predicate | coWriter |
P2389
|
FINISHED |
| Object |
Mike Taylor
Mike Taylor is a songwriter best known for co-writing John Denver’s classic folk song "Rocky Mountain High."
|
E790393
|
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: Mike Taylor | Statement: [Rocky Mountain High, coWriter, Mike Taylor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mike Taylor Context triple: [Rocky Mountain High, coWriter, Mike Taylor]
-
A.
Mike Taylor
Mike Taylor is a film editor known for his work on the acclaimed British gangster film "The Long Good Friday."
-
B.
Glen Taylor
Glen Taylor is an American billionaire businessman and politician best known as the longtime owner of the NBA’s Minnesota Timberwolves and WNBA’s Minnesota Lynx.
-
C.
Ian Taylor
Ian Taylor is a music producer known for his work on Gary Moore’s acclaimed blues-rock album "Still Got the Blues."
-
D.
Jim Taylor
Jim Taylor is an American film producer and screenwriter best known for his long-time collaboration with director Alexander Payne on acclaimed films such as "Sideways" and "Election."
-
E.
Gil Taylor
Gil Taylor was a renowned British cinematographer known for his innovative visual work on films such as "Star Wars," "Dr. Strangelove," and "A Hard Day's Night."
- 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: Mike Taylor Triple: [Rocky Mountain High, coWriter, Mike Taylor]
Generated description
Mike Taylor is a songwriter best known for co-writing John Denver’s classic folk song "Rocky Mountain High."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mike Taylor Target entity description: Mike Taylor is a songwriter best known for co-writing John Denver’s classic folk song "Rocky Mountain High."
-
A.
Mike Taylor
Mike Taylor is a film editor known for his work on the acclaimed British gangster film "The Long Good Friday."
-
B.
Glen Taylor
Glen Taylor is an American billionaire businessman and politician best known as the longtime owner of the NBA’s Minnesota Timberwolves and WNBA’s Minnesota Lynx.
-
C.
Ian Taylor
Ian Taylor is a music producer known for his work on Gary Moore’s acclaimed blues-rock album "Still Got the Blues."
-
D.
Jim Taylor
Jim Taylor is an American film producer and screenwriter best known for his long-time collaboration with director Alexander Payne on acclaimed films such as "Sideways" and "Election."
-
E.
Gil Taylor
Gil Taylor was a renowned British cinematographer known for his innovative visual work on films such as "Star Wars," "Dr. Strangelove," and "A Hard Day's Night."
- 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_69ca8424d0f08190831e2e93c6533aeb |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd1da7c1e08190af19169f5d806cde |
completed | April 1, 2026, 1:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b2735d788190bd8f963562fb85a8 |
completed | April 4, 2026, 6:40 a.m. |
| NEDg | Description generation | batch_69d0b4231b708190b8a4a342bc63e84d |
completed | April 4, 2026, 6:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d0b4b8131c8190b2aa8be56925b7bc |
completed | April 4, 2026, 6:50 a.m. |
Created at: March 30, 2026, 7:36 p.m.