Triple
T305799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lily Aldridge |
E6295
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object |
Laura Lyons
Laura Lyons is the mother of American fashion model Lily Aldridge.
|
E80097
|
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: Laura Lyons | Statement: [Lily Aldridge, parent, Laura Lyons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laura Lyons Context triple: [Lily Aldridge, parent, Laura Lyons]
-
A.
Katherine Rogers
Katherine Rogers was the mother of John Harvard, the English clergyman whose bequest helped found Harvard College in colonial Massachusetts.
-
B.
Lisa Rogers
Lisa Rogers is a member of the Rogers family, known as the daughter of Canadian businessman and media magnate Ted Rogers.
-
C.
Lisa Taylor
Lisa Taylor is known as the wife of American politician George Wallace, the former governor of Alabama.
-
D.
Sarah Cloyce
Sarah Cloyce was a woman accused during the Salem witch trials, known for being the sister of fellow accused Rebecca Nurse and for later helping to challenge the legitimacy of the proceedings.
-
E.
Rachel Marron
Rachel Marron is a famous pop singer and actress who becomes the client and love interest of a former Secret Service agent in the romantic thriller film "The Bodyguard."
- 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: Laura Lyons Triple: [Lily Aldridge, parent, Laura Lyons]
Generated description
Laura Lyons is the mother of American fashion model Lily Aldridge.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Laura Lyons Target entity description: Laura Lyons is the mother of American fashion model Lily Aldridge.
-
A.
Katherine Rogers
Katherine Rogers was the mother of John Harvard, the English clergyman whose bequest helped found Harvard College in colonial Massachusetts.
-
B.
Lisa Rogers
Lisa Rogers is a member of the Rogers family, known as the daughter of Canadian businessman and media magnate Ted Rogers.
-
C.
Lisa Taylor
Lisa Taylor is known as the wife of American politician George Wallace, the former governor of Alabama.
-
D.
Sarah Cloyce
Sarah Cloyce was a woman accused during the Salem witch trials, known for being the sister of fellow accused Rebecca Nurse and for later helping to challenge the legitimacy of the proceedings.
-
E.
Rachel Marron
Rachel Marron is a famous pop singer and actress who becomes the client and love interest of a former Secret Service agent in the romantic thriller film "The Bodyguard."
- 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_69a2e79230508190b912ecb555aae17e |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea2fba548190a5aeb1597dca96bd |
completed | Feb. 28, 2026, 1:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a573ff0574819083e39dc93de4311f |
completed | March 2, 2026, 11:26 a.m. |
| NEDg | Description generation | batch_69a574cd4970819085e97d86e47d2e7b |
completed | March 2, 2026, 11:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a57686f7dc8190a94e0f36cc47fa3a |
completed | March 2, 2026, 11:37 a.m. |
Created at: Feb. 28, 2026, 1:06 p.m.