Triple
T9245063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Hurt |
E222168
|
entity |
| Predicate | partner |
P1136
|
FINISHED |
| Object |
Sandra Jennings
Sandra Jennings is an American woman best known for her long-term relationship and legal disputes with actor William Hurt.
|
E908564
|
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: Sandra Jennings | Statement: [William Hurt, partner, Sandra Jennings]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandra Jennings Context triple: [William Hurt, partner, Sandra Jennings]
-
A.
Sandra Jolley
Sandra Jolley was the wife of American businessman and quality management expert Philip Crosby.
-
B.
Sandra Howard
Sandra Howard is a British former fashion model and novelist who became known as the wife of Conservative politician Michael Howard.
-
C.
Sandra Sully
Sandra Sully is a songwriter best known for co-writing the R&B classic "If You Think You’re Lonely Now."
-
D.
Sandra Denton
Sandra Denton, better known by her stage name Pepa, is a Jamaican-American rapper and actress best known as one-third of the pioneering hip hop group Salt-N-Pepa.
-
E.
Sandra Adair
Sandra Adair is an American film editor best known for her long-time collaboration with director Richard Linklater on films such as "Boyhood" and the "Before" trilogy.
- 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: Sandra Jennings Triple: [William Hurt, partner, Sandra Jennings]
Generated description
Sandra Jennings is an American woman best known for her long-term relationship and legal disputes with actor William Hurt.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sandra Jennings Target entity description: Sandra Jennings is an American woman best known for her long-term relationship and legal disputes with actor William Hurt.
-
A.
Sandra Jolley
Sandra Jolley was the wife of American businessman and quality management expert Philip Crosby.
-
B.
Sandra Howard
Sandra Howard is a British former fashion model and novelist who became known as the wife of Conservative politician Michael Howard.
-
C.
Sandra Sully
Sandra Sully is a songwriter best known for co-writing the R&B classic "If You Think You’re Lonely Now."
-
D.
Sandra Denton
Sandra Denton, better known by her stage name Pepa, is a Jamaican-American rapper and actress best known as one-third of the pioneering hip hop group Salt-N-Pepa.
-
E.
Sandra Adair
Sandra Adair is an American film editor best known for her long-time collaboration with director Richard Linklater on films such as "Boyhood" and the "Before" trilogy.
- 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_69ca83ee26cc81909ac624e190597d6d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cd03efaa748190973916bd790f6e3a |
completed | April 1, 2026, 11:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e462472ed88190a76b04157c235c80 |
completed | April 19, 2026, 5:04 a.m. |
| NEDg | Description generation | batch_69e46c3448348190b2c062d21771066d |
completed | April 19, 2026, 5:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69e46dadbc5c8190b41279a05731dc95 |
completed | April 19, 2026, 5:52 a.m. |
Created at: March 30, 2026, 7:30 p.m.