Triple
T19393274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Junebug |
E485120
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Mike S. Ryan
Mike S. Ryan is an American independent film producer known for his work on acclaimed art-house and character-driven films.
|
E1373612
|
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 S. Ryan | Statement: [Junebug, producer, Mike S. Ryan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mike S. Ryan Context triple: [Junebug, producer, Mike S. Ryan]
-
A.
Kevin P. Ryan
Kevin P. Ryan is an American entrepreneur and investor best known for founding and building multiple successful tech companies, including DoubleClick, Gilt Groupe, and MongoDB.
-
B.
Michael Ryan
Michael Ryan was the British gunman responsible for the 1987 Hungerford massacre, one of the deadliest mass shootings in UK history.
-
C.
Michael D. McDonough
Michael D. McDonough is an American local government official who serves as the mayor of Raytown, Missouri.
-
D.
Brian Rogers
Brian Rogers is a film producer best known for his work on the 2014 reboot of the Godzilla franchise.
-
E.
Richard Mullen
Richard Mullen is an American record producer and engineer best known for his work on Stevie Ray Vaughan’s landmark blues-rock albums, including "Texas Flood."
- 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 S. Ryan Triple: [Junebug, producer, Mike S. Ryan]
Generated description
Mike S. Ryan is an American independent film producer known for his work on acclaimed art-house and character-driven films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mike S. Ryan Target entity description: Mike S. Ryan is an American independent film producer known for his work on acclaimed art-house and character-driven films.
-
A.
Kevin P. Ryan
Kevin P. Ryan is an American entrepreneur and investor best known for founding and building multiple successful tech companies, including DoubleClick, Gilt Groupe, and MongoDB.
-
B.
Michael Ryan
Michael Ryan was the British gunman responsible for the 1987 Hungerford massacre, one of the deadliest mass shootings in UK history.
-
C.
Michael D. McDonough
Michael D. McDonough is an American local government official who serves as the mayor of Raytown, Missouri.
-
D.
Brian Rogers
Brian Rogers is a film producer best known for his work on the 2014 reboot of the Godzilla franchise.
-
E.
Richard Mullen
Richard Mullen is an American record producer and engineer best known for his work on Stevie Ray Vaughan’s landmark blues-rock albums, including "Texas Flood."
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b468dd88190acd82b4ee33bd39b |
completed | April 20, 2026, 12:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a072b8951648190a7ea05504c3cd9c1 |
completed | May 15, 2026, 2:19 p.m. |
| NEDg | Description generation | batch_6a072e2e59388190ac5a6a9479555154 |
completed | May 15, 2026, 2:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a072eb872b88190904f9947228066fb |
completed | May 15, 2026, 2:33 p.m. |
Created at: April 10, 2026, 1:36 p.m.