Triple
T23197218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Owens-Illinois |
E579904
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Michael J. Owens
Michael J. Owens was an American inventor and industrialist best known for revolutionizing the glass industry by developing the first fully automatic bottle-making machine.
|
E1575358
|
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: Michael J. Owens | Statement: [Owens-Illinois, foundedBy, Michael J. Owens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael J. Owens Context triple: [Owens-Illinois, foundedBy, Michael J. Owens]
-
A.
Richard A. Roth
Richard A. Roth is an American film producer best known for his work on the 1986 crime thriller "Manhunter."
-
B.
Michael Wittenberg
Michael Wittenberg was an investment adviser best known as the late husband of Broadway star Bernadette Peters.
-
C.
Michael J. Ozier
Michael J. Ozier is a cinematographer best known for his work on the film "CBGB," which chronicles the iconic New York punk rock club.
-
D.
Michael Winder
Michael Winder is a screenwriter best known for his work on the 1976 action film "Killer Force."
-
E.
Michael Gunton
Michael Gunton is a British television producer best known for his work on major BBC natural history series such as Planet Earth II and Dynasties.
- 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: Michael J. Owens Triple: [Owens-Illinois, foundedBy, Michael J. Owens]
Generated description
Michael J. Owens was an American inventor and industrialist best known for revolutionizing the glass industry by developing the first fully automatic bottle-making machine.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Michael J. Owens Target entity description: Michael J. Owens was an American inventor and industrialist best known for revolutionizing the glass industry by developing the first fully automatic bottle-making machine.
-
A.
Richard A. Roth
Richard A. Roth is an American film producer best known for his work on the 1986 crime thriller "Manhunter."
-
B.
Michael Wittenberg
Michael Wittenberg was an investment adviser best known as the late husband of Broadway star Bernadette Peters.
-
C.
Michael J. Ozier
Michael J. Ozier is a cinematographer best known for his work on the film "CBGB," which chronicles the iconic New York punk rock club.
-
D.
Michael Winder
Michael Winder is a screenwriter best known for his work on the 1976 action film "Killer Force."
-
E.
Michael Gunton
Michael Gunton is a British television producer best known for his work on major BBC natural history series such as Planet Earth II and Dynasties.
- 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_69e24600eed08190bd7e5295653a1503 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fdc0b8081909242fdc5cb1da517 |
completed | April 29, 2026, 4:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c30bebfe48190944c0933ea100b11 |
completed | May 19, 2026, 9:43 a.m. |
| NEDg | Description generation | batch_6a0c330135cc8190b5a0e512bda6277d |
completed | May 19, 2026, 9:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c375dd5a4819097a80ae43a1c4442 |
completed | May 19, 2026, 10:11 a.m. |
Created at: April 17, 2026, 4:06 p.m.