Triple
T1182172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louis Calhern |
E25161
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Marianne Stewart
Marianne Stewart was an American actress active in mid-20th-century film, television, and theater.
|
E171666
|
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: Marianne Stewart | Statement: [Louis Calhern, spouse, Marianne Stewart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marianne Stewart Context triple: [Louis Calhern, spouse, Marianne Stewart]
-
A.
Esti Maxine Stephens
Esti Maxine Stephens is the daughter of model and television personality Chrissy Teigen and musician John Legend.
-
B.
Ruby Aldridge
Ruby Aldridge is an American fashion model known for her runway and editorial work with major designers and magazines.
-
C.
Candy Clark
Candy Clark is an American actress best known for her Academy Award–nominated role in the coming-of-age film "American Graffiti."
-
D.
Eboni Mills
Eboni Mills is known for having been married to RZA, the influential producer and de facto leader of the Wu-Tang Clan.
-
E.
Brenda Leigh Johnson
Brenda Leigh Johnson is the sharp, determined Deputy Chief of the LAPD’s Major Crimes Division in the TV series "The Closer," known for her exceptional interrogation skills and unorthodox but effective investigative methods.
- 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: Marianne Stewart Triple: [Louis Calhern, spouse, Marianne Stewart]
Generated description
Marianne Stewart was an American actress active in mid-20th-century film, television, and theater.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marianne Stewart Target entity description: Marianne Stewart was an American actress active in mid-20th-century film, television, and theater.
-
A.
Esti Maxine Stephens
Esti Maxine Stephens is the daughter of model and television personality Chrissy Teigen and musician John Legend.
-
B.
Ruby Aldridge
Ruby Aldridge is an American fashion model known for her runway and editorial work with major designers and magazines.
-
C.
Candy Clark
Candy Clark is an American actress best known for her Academy Award–nominated role in the coming-of-age film "American Graffiti."
-
D.
Eboni Mills
Eboni Mills is known for having been married to RZA, the influential producer and de facto leader of the Wu-Tang Clan.
-
E.
Brenda Leigh Johnson
Brenda Leigh Johnson is the sharp, determined Deputy Chief of the LAPD’s Major Crimes Division in the TV series "The Closer," known for her exceptional interrogation skills and unorthodox but effective investigative methods.
- 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_69a494267b4c819088c97a59182bf56a |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd347d4481909e9094463011289d |
completed | March 1, 2026, 10:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad231945048190be6536b4a71334aa |
completed | March 8, 2026, 7:19 a.m. |
| NEDg | Description generation | batch_69ad23cbe87c81909b745ecaadf77bce |
completed | March 8, 2026, 7:22 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad24224af08190a1a03c0f1d363ce0 |
completed | March 8, 2026, 7:24 a.m. |
Created at: March 1, 2026, 7:45 p.m.