Triple
T15702130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spirit |
E380617
|
entity |
| Predicate | member |
P10
|
FINISHED |
| Object |
Mark Andes
Mark Andes is an American bassist best known for his work with the rock bands Spirit, Jo Jo Gunne, and Heart.
|
E1176389
|
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: Mark Andes | Statement: [Spirit, member, Mark Andes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Andes Context triple: [Spirit, member, Mark Andes]
-
A.
Keith Andes
Keith Andes was an American actor known for his work in mid-20th-century film, television, and theater, including notable roles in productions like "A Date with Judy" and "This Man Is Mine."
-
B.
Matthew Anden
Matthew Anden was a German-born American actor known for his work in film and theater, including a role in the psychological drama "David and Lisa."
-
C.
Bryan Englund
Bryan Englund was the son of American film director and producer George Englund and actress Cloris Leachman.
-
D.
Michael Andrews
Michael Andrews is an American film composer and musician known for his atmospheric scores for movies such as Donnie Darko and Bridesmaids.
-
E.
Michael Andrews
Michael Andrews is a film editor best known for his work on major animated features, including the comedy sequel "Shrek the Third."
- 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: Mark Andes Triple: [Spirit, member, Mark Andes]
Generated description
Mark Andes is an American bassist best known for his work with the rock bands Spirit, Jo Jo Gunne, and Heart.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mark Andes Target entity description: Mark Andes is an American bassist best known for his work with the rock bands Spirit, Jo Jo Gunne, and Heart.
-
A.
Keith Andes
Keith Andes was an American actor known for his work in mid-20th-century film, television, and theater, including notable roles in productions like "A Date with Judy" and "This Man Is Mine."
-
B.
Matthew Anden
Matthew Anden was a German-born American actor known for his work in film and theater, including a role in the psychological drama "David and Lisa."
-
C.
Bryan Englund
Bryan Englund was the son of American film director and producer George Englund and actress Cloris Leachman.
-
D.
Michael Andrews
Michael Andrews is an American film composer and musician known for his atmospheric scores for movies such as Donnie Darko and Bridesmaids.
-
E.
Michael Andrews
Michael Andrews is a film editor best known for his work on major animated features, including the comedy sequel "Shrek the Third."
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f6e965881909319f85c51c6fb74 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff9090e25481909f142b54ac4802f8 |
completed | May 9, 2026, 7:52 p.m. |
| NEDg | Description generation | batch_69ff92d044f48190baefcf932f369350 |
completed | May 9, 2026, 8:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff934af4288190b3d3cad6af142334 |
completed | May 9, 2026, 8:04 p.m. |
Created at: April 10, 2026, 4:45 a.m.