Triple
T11954848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed Balls |
E284523
|
entity |
| Predicate | hasSibling |
P363
|
FINISHED |
| Object |
Andrew Balls
Andrew Balls is a British economist and investment executive known for his senior leadership roles at the asset management firm PIMCO.
|
E956026
|
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 Balls | Statement: [Ed Balls, hasSibling, Andrew Balls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Balls Context triple: [Ed Balls, hasSibling, Andrew Balls]
-
A.
Fred Ball
Fred Ball is a film producer best known for his work on the cult classic crime-romance movie "True Romance."
-
B.
Martin Ball
Martin Ball is a British actor known for his work in theatre, television, and musical productions in the UK.
-
C.
Grant Bowler
Grant Bowler is an Australian actor known for his roles in television series such as "Defiance," "Ugly Betty," and "True Blood."
-
D.
Andrew J. Ballard
Andrew J. Ballard is a scientific researcher and co-author of a 2021 Nature publication by Jumper et al., likely contributing to advances in computational biology or protein structure prediction.
-
E.
Sam Ball
Sam Ball is an actor known for his supporting role in the romantic comedy film "13 Going on 30."
- 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 Balls Triple: [Ed Balls, hasSibling, Andrew Balls]
Generated description
Andrew Balls is a British economist and investment executive known for his senior leadership roles at the asset management firm PIMCO.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Andrew Balls Target entity description: Andrew Balls is a British economist and investment executive known for his senior leadership roles at the asset management firm PIMCO.
-
A.
Fred Ball
Fred Ball is a film producer best known for his work on the cult classic crime-romance movie "True Romance."
-
B.
Martin Ball
Martin Ball is a British actor known for his work in theatre, television, and musical productions in the UK.
-
C.
Grant Bowler
Grant Bowler is an Australian actor known for his roles in television series such as "Defiance," "Ugly Betty," and "True Blood."
-
D.
Andrew J. Ballard
Andrew J. Ballard is a scientific researcher and co-author of a 2021 Nature publication by Jumper et al., likely contributing to advances in computational biology or protein structure prediction.
-
E.
Sam Ball
Sam Ball is an actor known for his supporting role in the romantic comedy film "13 Going on 30."
- 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_69d6ab2db38c8190b1f0ed6663ef8ada |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d90366fda8819083168c93abad27d4 |
completed | April 10, 2026, 2:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f459175f808190974ac70431f35c74 |
completed | May 1, 2026, 7:41 a.m. |
| NEDg | Description generation | batch_69f4645a7038819089d7533715f8a430 |
completed | May 1, 2026, 8:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f4664ff9608190b23e29b3e5c1c326 |
completed | May 1, 2026, 8:37 a.m. |
Created at: April 8, 2026, 9:45 p.m.