Triple
T2315430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Hart |
E51051
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Eniko Parrish
Eniko Parrish is an American model and media personality best known as the wife of comedian and actor Kevin Hart.
|
E326584
|
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: Eniko Parrish | Statement: [Kevin Hart, spouse, Eniko Parrish]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eniko Parrish Context triple: [Kevin Hart, spouse, Eniko Parrish]
-
A.
Colleen Sostorics
Colleen Sostorics is a Canadian former ice hockey defenceman and three-time Olympic gold medallist who starred with the national women’s team.
-
B.
Elizabeth Roboz
Elizabeth Roboz was a Hungarian-American neurobiologist and biochemist known for her research on brain chemistry and her marriage to Hans Albert Einstein, the son of Albert Einstein.
-
C.
Anna Nolin
Anna Nolin is an American educator and school district leader who serves as superintendent of the Newton Public Schools in Massachusetts.
-
D.
Rose Lorkowski
Rose Lorkowski is the struggling single mother and former high school cheerleader who starts a crime-scene cleanup business in the film "Sunshine Cleaning."
-
E.
Emily Dreyfuss
Emily Dreyfuss is an American journalist and writer known for her work on technology, politics, and digital culture for outlets such as WIRED and the Harvard Shorenstein Center.
- 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: Eniko Parrish Triple: [Kevin Hart, spouse, Eniko Parrish]
Generated description
Eniko Parrish is an American model and media personality best known as the wife of comedian and actor Kevin Hart.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Eniko Parrish Target entity description: Eniko Parrish is an American model and media personality best known as the wife of comedian and actor Kevin Hart.
-
A.
Colleen Sostorics
Colleen Sostorics is a Canadian former ice hockey defenceman and three-time Olympic gold medallist who starred with the national women’s team.
-
B.
Elizabeth Roboz
Elizabeth Roboz was a Hungarian-American neurobiologist and biochemist known for her research on brain chemistry and her marriage to Hans Albert Einstein, the son of Albert Einstein.
-
C.
Anna Nolin
Anna Nolin is an American educator and school district leader who serves as superintendent of the Newton Public Schools in Massachusetts.
-
D.
Rose Lorkowski
Rose Lorkowski is the struggling single mother and former high school cheerleader who starts a crime-scene cleanup business in the film "Sunshine Cleaning."
-
E.
Emily Dreyfuss
Emily Dreyfuss is an American journalist and writer known for her work on technology, politics, and digital culture for outlets such as WIRED and the Harvard Shorenstein Center.
- 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_69a88b074b908190ae983dbca7757d88 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc61e72508190b335cda2c7fef130 |
completed | March 7, 2026, 6:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b20321518c8190a221620074f3428b |
completed | March 12, 2026, 12:04 a.m. |
| NEDg | Description generation | batch_69b20532b7388190be5f7bcf48db6f45 |
completed | March 12, 2026, 12:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b2058d7c4c8190a44fc8745df3b1b3 |
completed | March 12, 2026, 12:15 a.m. |
Created at: March 4, 2026, 7:49 p.m.