Triple
T21481764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marc Platt |
E530009
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Jean Platt
Jean Platt is known as the wife of American film and theater producer Marc Platt.
|
E1485935
|
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: Jean Platt | Statement: [Marc Platt, spouse, Jean Platt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean Platt Context triple: [Marc Platt, spouse, Jean Platt]
-
A.
Liz Imbrie
Liz Imbrie is a witty, sardonic magazine reporter who serves as a key supporting character and romantic foil in the musical film "High Society."
-
B.
Sandra Lovelock
Sandra Lovelock is known as the wife of British scientist James Lovelock, the originator of the Gaia hypothesis.
-
C.
Margaret Rock
Margaret Rock was a British mathematician and cryptanalyst who played a key role in codebreaking German ciphers at Bletchley Park during World War II.
-
D.
Elizabeth Lloyd
Elizabeth Lloyd was a member of a prominent colonial Pennsylvania family who became the wife of American Revolutionary War general and Philadelphia political leader John Cadwalader.
-
E.
Carlye Adler
Carlye Adler is a journalist and author known for co-writing business and leadership books with prominent entrepreneurs and executives.
- 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: Jean Platt Triple: [Marc Platt, spouse, Jean Platt]
Generated description
Jean Platt is known as the wife of American film and theater producer Marc Platt.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jean Platt Target entity description: Jean Platt is known as the wife of American film and theater producer Marc Platt.
-
A.
Liz Imbrie
Liz Imbrie is a witty, sardonic magazine reporter who serves as a key supporting character and romantic foil in the musical film "High Society."
-
B.
Sandra Lovelock
Sandra Lovelock is known as the wife of British scientist James Lovelock, the originator of the Gaia hypothesis.
-
C.
Margaret Rock
Margaret Rock was a British mathematician and cryptanalyst who played a key role in codebreaking German ciphers at Bletchley Park during World War II.
-
D.
Elizabeth Lloyd
Elizabeth Lloyd was a member of a prominent colonial Pennsylvania family who became the wife of American Revolutionary War general and Philadelphia political leader John Cadwalader.
-
E.
Carlye Adler
Carlye Adler is a journalist and author known for co-writing business and leadership books with prominent entrepreneurs and executives.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea338f988190a3044f8d02a567fe |
completed | April 23, 2026, 9:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09d001a198819092af8bb244511d6b |
completed | May 17, 2026, 2:26 p.m. |
| NEDg | Description generation | batch_6a09d07bfe6881908e76b8bd67985322 |
completed | May 17, 2026, 2:28 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09d19bac548190b78121d21108ecd2 |
completed | May 17, 2026, 2:32 p.m. |
Created at: April 16, 2026, 6:21 p.m.