Triple
T6706149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew Lewis |
E153008
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Angela Jones
Angela Jones is known as the wife of British actor Matthew Lewis, who played Neville Longbottom in the Harry Potter film series.
|
E614170
|
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: Angela Jones | Statement: [Matthew Lewis, spouse, Angela Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angela Jones Context triple: [Matthew Lewis, spouse, Angela Jones]
-
A.
Angela Quarles
Angela Quarles is a contemporary American author best known for her time-travel and paranormal romance novels.
-
B.
Angela Barnes
Angela Barnes is a British stand-up comedian and radio presenter known for her sharp, politically savvy comedy and regular appearances on BBC Radio 4.
-
C.
Angela Browne
Angela Browne was a British actress known for her film and television roles in the 1950s and 1960s.
-
D.
Angela James
Angela James is a pioneering Canadian ice hockey player widely regarded as one of the greatest women’s players of all time and a trailblazer for the women’s game.
-
E.
Angela Beesley
Angela Beesley is a British web entrepreneur best known as the co-founder of Wikia (now Fandom), a major community-driven wiki hosting platform.
- 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: Angela Jones Triple: [Matthew Lewis, spouse, Angela Jones]
Generated description
Angela Jones is known as the wife of British actor Matthew Lewis, who played Neville Longbottom in the Harry Potter film series.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Angela Jones Target entity description: Angela Jones is known as the wife of British actor Matthew Lewis, who played Neville Longbottom in the Harry Potter film series.
-
A.
Angela Quarles
Angela Quarles is a contemporary American author best known for her time-travel and paranormal romance novels.
-
B.
Angela Barnes
Angela Barnes is a British stand-up comedian and radio presenter known for her sharp, politically savvy comedy and regular appearances on BBC Radio 4.
-
C.
Angela Browne
Angela Browne was a British actress known for her film and television roles in the 1950s and 1960s.
-
D.
Angela James
Angela James is a pioneering Canadian ice hockey player widely regarded as one of the greatest women’s players of all time and a trailblazer for the women’s game.
-
E.
Angela Beesley
Angela Beesley is a British web entrepreneur best known as the co-founder of Wikia (now Fandom), a major community-driven wiki hosting platform.
- 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_69c68808d8d8819087369015270788fe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d0ea8cfc819081affc73603c2cf3 |
completed | March 27, 2026, 6:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7008aeac08190887a7bf5703b69f4 |
completed | March 27, 2026, 10:11 p.m. |
| NEDg | Description generation | batch_69c7067a932c8190a039a9ab2fd5d8a5 |
completed | March 27, 2026, 10:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7073483a4819084392c89a84f63b1 |
completed | March 27, 2026, 10:39 p.m. |
Created at: March 27, 2026, 2:06 p.m.