Triple
T22655330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Company (2018 West End revival) |
E559207
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Rebecca Lock
Rebecca Lock is a British stage actress known for her performances in major West End musical theatre productions.
|
E1557351
|
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: Rebecca Lock | Statement: [Company (2018 West End revival), starring, Rebecca Lock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rebecca Lock Context triple: [Company (2018 West End revival), starring, Rebecca Lock]
-
A.
Rebecca Lovell
Rebecca Lovell is an American musician best known as the vocalist and multi-instrumentalist of the roots-rock duo Larkin Poe.
-
B.
Rebecca Laurie
Rebecca Laurie is a daughter of British actor and comedian Hugh Laurie.
-
C.
Rebecca Welton
Rebecca Welton is a fictional football club owner and central character in the television series "Ted Lasso."
-
D.
Rebecca Blunt
Rebecca Blunt is a screenwriter best known for penning the heist comedy film "Logan Lucky."
-
E.
Rebecca Hazlewood
Rebecca Hazlewood is a British actress best known for her role as Asha in the NBC sitcom "Outsourced" and for appearances in various British and American television series.
- 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: Rebecca Lock Triple: [Company (2018 West End revival), starring, Rebecca Lock]
Generated description
Rebecca Lock is a British stage actress known for her performances in major West End musical theatre productions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rebecca Lock Target entity description: Rebecca Lock is a British stage actress known for her performances in major West End musical theatre productions.
-
A.
Rebecca Lovell
Rebecca Lovell is an American musician best known as the vocalist and multi-instrumentalist of the roots-rock duo Larkin Poe.
-
B.
Rebecca Laurie
Rebecca Laurie is a daughter of British actor and comedian Hugh Laurie.
-
C.
Rebecca Welton
Rebecca Welton is a fictional football club owner and central character in the television series "Ted Lasso."
-
D.
Rebecca Blunt
Rebecca Blunt is a screenwriter best known for penning the heist comedy film "Logan Lucky."
-
E.
Rebecca Hazlewood
Rebecca Hazlewood is a British actress best known for her role as Asha in the NBC sitcom "Outsourced" and for appearances in various British and American television series.
- 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_69e245489dd88190b1f674acf61c8769 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1765b93dc8190a0357dd4b6ae524a |
completed | April 29, 2026, 3:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ba797ca788190a9ad4abd08505e60 |
completed | May 18, 2026, 11:58 p.m. |
| NEDg | Description generation | batch_6a0ba8a7d42081909eb748c3465ad19d |
completed | May 19, 2026, 12:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ba955e07c819091a8f7a51cecd4bc |
completed | May 19, 2026, 12:05 a.m. |
Created at: April 17, 2026, 3:06 p.m.