Triple
T18768561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celestron |
E458953
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Tom Johnson
Tom Johnson was an American engineer and entrepreneur best known as the founder of the telescope and optics company Celestron.
|
E1343623
|
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: Tom Johnson | Statement: [Celestron, foundedBy, Tom Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Johnson Context triple: [Celestron, foundedBy, Tom Johnson]
-
A.
Tom Johnson
Tom Johnson is an American former professional boxer and long-reigning IBF featherweight champion known for his title defenses in the 1990s.
-
B.
Will Johnson
Will Johnson is an actor known for his work on the British stage and screen, including appearing in the National Theatre’s 2013 production of Othello.
-
C.
Bruce Douglas Johnson
Bruce Douglas Johnson is a cinematographer best known for his work on the stoner comedy film "Harold & Kumar Go to White Castle."
-
D.
John Johnson
John Johnson was a versatile American professional basketball forward best known for his key role with the Seattle SuperSonics during their late-1970s championship runs.
-
E.
John Johnson
John Johnson was a prominent British colonial official and military leader who commanded Indigenous auxiliaries during conflicts in North America.
- 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: Tom Johnson Triple: [Celestron, foundedBy, Tom Johnson]
Generated description
Tom Johnson was an American engineer and entrepreneur best known as the founder of the telescope and optics company Celestron.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tom Johnson Target entity description: Tom Johnson was an American engineer and entrepreneur best known as the founder of the telescope and optics company Celestron.
-
A.
Tom Johnson
Tom Johnson is an American former professional boxer and long-reigning IBF featherweight champion known for his title defenses in the 1990s.
-
B.
Will Johnson
Will Johnson is an actor known for his work on the British stage and screen, including appearing in the National Theatre’s 2013 production of Othello.
-
C.
Bruce Douglas Johnson
Bruce Douglas Johnson is a cinematographer best known for his work on the stoner comedy film "Harold & Kumar Go to White Castle."
-
D.
John Johnson
John Johnson was a versatile American professional basketball forward best known for his key role with the Seattle SuperSonics during their late-1970s championship runs.
-
E.
John Johnson
John Johnson was a prominent British colonial official and military leader who commanded Indigenous auxiliaries during conflicts in North America.
- 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e58d867264819098ae35c9feab3bb4 |
completed | April 20, 2026, 2:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a054710894c819097fc5cd9753a9c94 |
completed | May 14, 2026, 3:52 a.m. |
| NEDg | Description generation | batch_6a054b1a8698819090e8594f00588703 |
completed | May 14, 2026, 4:10 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a054b881bd48190ab3ae42719357d7c |
completed | May 14, 2026, 4:11 a.m. |
Created at: April 10, 2026, 11:52 a.m.