Triple
T20392567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nichelle Nichols |
E498118
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object |
Kyle Johnson
Kyle Johnson is the son of actress Nichelle Nichols, best known for her groundbreaking role as Lieutenant Uhura on Star Trek.
|
E1435263
|
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: Kyle Johnson | Statement: [Nichelle Nichols, child, Kyle Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kyle Johnson Context triple: [Nichelle Nichols, child, Kyle Johnson]
-
A.
Nick Johnson
Nick Johnson is a film editor best known for his work on the innovative screen-based thriller "Searching" (2018).
-
B.
Jamie Johnson
Jamie Johnson is an American documentary filmmaker and heir to the Johnson & Johnson family fortune, known for exploring themes of wealth and social class.
-
C.
Connor Johnson
Connor Johnson is a professional basketball coach recognized as the NBA G League Coach of the Year for the 2020–21 season.
-
D.
Brett Johnson
Brett Johnson is a television writer and producer best known for his work on acclaimed limited series such as "Escape at Dannemora."
-
E.
Cole Johnson
Cole Johnson is the young protagonist of the horror-comedy film "The Babysitter," whose seemingly ordinary night at home spirals into a violent and bizarre fight for survival.
- 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: Kyle Johnson Triple: [Nichelle Nichols, child, Kyle Johnson]
Generated description
Kyle Johnson is the son of actress Nichelle Nichols, best known for her groundbreaking role as Lieutenant Uhura on Star Trek.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kyle Johnson Target entity description: Kyle Johnson is the son of actress Nichelle Nichols, best known for her groundbreaking role as Lieutenant Uhura on Star Trek.
-
A.
Nick Johnson
Nick Johnson is a film editor best known for his work on the innovative screen-based thriller "Searching" (2018).
-
B.
Jamie Johnson
Jamie Johnson is an American documentary filmmaker and heir to the Johnson & Johnson family fortune, known for exploring themes of wealth and social class.
-
C.
Connor Johnson
Connor Johnson is a professional basketball coach recognized as the NBA G League Coach of the Year for the 2020–21 season.
-
D.
Brett Johnson
Brett Johnson is a television writer and producer best known for his work on acclaimed limited series such as "Escape at Dannemora."
-
E.
Cole Johnson
Cole Johnson is the young protagonist of the horror-comedy film "The Babysitter," whose seemingly ordinary night at home spirals into a violent and bizarre fight for survival.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e679108b1481909677cf80e8e77e76 |
completed | April 20, 2026, 7:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a089d25c1fc8190b0c78459e7f9c955 |
completed | May 16, 2026, 4:36 p.m. |
| NEDg | Description generation | batch_6a089e379e108190b195ce87299e8e2f |
completed | May 16, 2026, 4:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a089e9a267c8190b60806eca6502acc |
completed | May 16, 2026, 4:43 p.m. |
Created at: April 16, 2026, 11:28 a.m.