Triple
T23004932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack White |
E572736
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Karen Elson
Karen Elson is an English supermodel and singer-songwriter known for her high-fashion runway and editorial work as well as her solo music career.
|
E1568437
|
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: Karen Elson | Statement: [Jack White, spouse, Karen Elson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karen Elson Context triple: [Jack White, spouse, Karen Elson]
-
A.
Hayley Schore
Hayley Schore is a television writer and producer best known for co-creating the medical drama series "The Resident."
-
B.
Rachel Van Dyken
Rachel Van Dyken is a contemporary American author best known for her popular romance novels and New York Times bestselling series.
-
C.
Lauren Lapkus
Lauren Lapkus is an American actress and comedian known for her roles in television series like "Orange Is the New Black" and numerous film and podcast appearances.
-
D.
Nicole Eggert
Nicole Eggert is an American actress best known for her role as Summer Quinn on the television series "Baywatch."
-
E.
Teala Loring
Teala Loring was an American film actress of the 1940s, known for her supporting roles in Hollywood features and as one of several sisters who also worked in the entertainment industry.
- 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: Karen Elson Triple: [Jack White, spouse, Karen Elson]
Generated description
Karen Elson is an English supermodel and singer-songwriter known for her high-fashion runway and editorial work as well as her solo music career.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Karen Elson Target entity description: Karen Elson is an English supermodel and singer-songwriter known for her high-fashion runway and editorial work as well as her solo music career.
-
A.
Hayley Schore
Hayley Schore is a television writer and producer best known for co-creating the medical drama series "The Resident."
-
B.
Rachel Van Dyken
Rachel Van Dyken is a contemporary American author best known for her popular romance novels and New York Times bestselling series.
-
C.
Lauren Lapkus
Lauren Lapkus is an American actress and comedian known for her roles in television series like "Orange Is the New Black" and numerous film and podcast appearances.
-
D.
Nicole Eggert
Nicole Eggert is an American actress best known for her role as Summer Quinn on the television series "Baywatch."
-
E.
Teala Loring
Teala Loring was an American film actress of the 1940s, known for her supporting roles in Hollywood features and as one of several sisters who also worked in the entertainment industry.
- 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_69e245b6a3ac81908087599eefe3e365 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18356417881908c8d6ee56bdc85f5 |
completed | April 29, 2026, 4:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c0acabb808190a688aacdf935a9ad |
completed | May 19, 2026, 7:01 a.m. |
| NEDg | Description generation | batch_6a0c0f7adc1881909118993546f0a702 |
completed | May 19, 2026, 7:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c0ff32c2c81909a4c2555c6769cdd |
completed | May 19, 2026, 7:23 a.m. |
Created at: April 17, 2026, 3:51 p.m.