Triple
T22657704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brunel University London |
E559271
|
entity |
| Predicate | hasViceChancellor |
P142
|
FINISHED |
| Object |
Andrew Jones
Andrew Jones is a British academic and university leader who serves as the Vice-Chancellor of Brunel University London.
|
E1549285
|
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: Andrew Jones | Statement: [Brunel University London, hasViceChancellor, Andrew Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Jones Context triple: [Brunel University London, hasViceChancellor, Andrew Jones]
-
A.
Matt Jones
Matt Jones is an American actor and comedian best known for his roles in television series like "Breaking Bad" and for his extensive voice work in animated shows and video games.
-
B.
Matt Jones
Matt Jones is a British musician best known as a former member of the rock band Beady Eye, formed by ex-Oasis members.
-
C.
Matt Jones
Matt Jones is a musician best known as a former member of the American pop-punk band The Hi-Fives.
-
D.
Ken Jones
Ken Jones was a prominent African American LGBTQ activist and community organizer known for his work in San Francisco’s gay rights and HIV/AIDS movements.
-
E.
Ken Jones
Ken Jones was a British composer and conductor best known for his film and television scores in the mid-20th century.
- 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: Andrew Jones Triple: [Brunel University London, hasViceChancellor, Andrew Jones]
Generated description
Andrew Jones is a British academic and university leader who serves as the Vice-Chancellor of Brunel University London.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Andrew Jones Target entity description: Andrew Jones is a British academic and university leader who serves as the Vice-Chancellor of Brunel University London.
-
A.
Matt Jones
Matt Jones is an American actor and comedian best known for his roles in television series like "Breaking Bad" and for his extensive voice work in animated shows and video games.
-
B.
Matt Jones
Matt Jones is a musician best known as a former member of the American pop-punk band The Hi-Fives.
-
C.
Matt Jones
Matt Jones is a British musician best known as a former member of the rock band Beady Eye, formed by ex-Oasis members.
-
D.
Ken Jones
Ken Jones was a British composer and conductor best known for his film and television scores in the mid-20th century.
-
E.
Ken Jones
Ken Jones was a prominent African American LGBTQ activist and community organizer known for his work in San Francisco’s gay rights and HIV/AIDS movements.
- 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_69f1765d10588190b4574f3e64617cd4 |
completed | April 29, 2026, 3:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b73e246408190b4cab82e6799f162 |
completed | May 18, 2026, 8:17 p.m. |
| NEDg | Description generation | batch_6a0b77402cf48190999a8e99f69bd480 |
completed | May 18, 2026, 8:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b77c92d6081909abd6f1280dc22f7 |
completed | May 18, 2026, 8:34 p.m. |
Created at: April 17, 2026, 3:07 p.m.