Triple
T3795881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ralph J. Roberts |
E89767
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object |
Lisa Roberts
Lisa Roberts is one of the children of Ralph J. Roberts, the American businessman best known as a co-founder of Comcast.
|
E389572
|
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: Lisa Roberts | Statement: [Ralph J. Roberts, child, Lisa Roberts]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lisa Roberts Context triple: [Ralph J. Roberts, child, Lisa Roberts]
-
A.
Lynette White
Lynette White is a character in the television series "The District," which follows the professional and personal lives of law enforcement officials in Washington, D.C.
-
B.
Marla Gibbs
Marla Gibbs is an American actress and comedian best known for her Emmy-nominated role as the sharp-tongued maid Florence Johnston on the classic sitcom "The Jeffersons."
-
C.
Lisa Rogers
Lisa Rogers is a member of the Rogers family, known as the daughter of Canadian businessman and media magnate Ted Rogers.
-
D.
Elizabeth Watson
Elizabeth Watson is known as the wife of molecular biologist and DNA double-helix co-discoverer James Watson.
-
E.
Meredith Vickers
Meredith Vickers is a cold, authoritative Weyland Corporation executive who oversees the Prometheus mission in the 2012 science fiction film "Prometheus."
- 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: Lisa Roberts Triple: [Ralph J. Roberts, child, Lisa Roberts]
Generated description
Lisa Roberts is one of the children of Ralph J. Roberts, the American businessman best known as a co-founder of Comcast.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lisa Roberts Target entity description: Lisa Roberts is one of the children of Ralph J. Roberts, the American businessman best known as a co-founder of Comcast.
-
A.
Lynette White
Lynette White is a character in the television series "The District," which follows the professional and personal lives of law enforcement officials in Washington, D.C.
-
B.
Marla Gibbs
Marla Gibbs is an American actress and comedian best known for her Emmy-nominated role as the sharp-tongued maid Florence Johnston on the classic sitcom "The Jeffersons."
-
C.
Lisa Rogers
Lisa Rogers is a member of the Rogers family, known as the daughter of Canadian businessman and media magnate Ted Rogers.
-
D.
Elizabeth Watson
Elizabeth Watson is known as the wife of molecular biologist and DNA double-helix co-discoverer James Watson.
-
E.
Meredith Vickers
Meredith Vickers is a cold, authoritative Weyland Corporation executive who oversees the Prometheus mission in the 2012 science fiction film "Prometheus."
- 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_69aed9597d6881909b6ee3b9de859223 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee79f09bc8190b7514a11a030eba5 |
completed | March 9, 2026, 3:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f05ea5e081908c4714ca35aed48b |
completed | March 14, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_69b4f2ed663c8190be431c7aae60259e |
completed | March 14, 2026, 5:32 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4f72eba988190acb96b44fc8b7c30 |
completed | March 14, 2026, 5:50 a.m. |
Created at: March 9, 2026, 3:15 p.m.