Triple
T18569850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pat Cummins |
E453845
|
entity |
| Predicate | hasSibling |
P363
|
FINISHED |
| Object |
Matt Cummins
Matt Cummins is an Australian man best known as the brother of international cricketer Pat Cummins.
|
E1395917
|
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: Matt Cummins | Statement: [Pat Cummins, hasSibling, Matt Cummins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Cummins Context triple: [Pat Cummins, hasSibling, Matt Cummins]
-
A.
Jeff Cummins
Jeff Cummins is an illustrator best known for his striking cover art on science fiction and fantasy publications, including numerous Doctor Who titles.
-
B.
Michael McCusker
Michael McCusker is an American film editor known for his work on major Hollywood productions, including the thriller "The Girl on the Train" (2016).
-
C.
Kevin McLaughlin
Kevin McLaughlin is a literary scholar and translator known for his English translation of Walter Benjamin’s "The Arcades Project."
-
D.
Christian McLaughlin
Christian McLaughlin is a television producer and writer known for his work on various comedy and genre projects, including the film "The Invisible Woman."
-
E.
Kevin Duggan
Kevin Duggan is a relatively obscure individual whose name is shared with multiple people across different professions, such as sports and public service.
- 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: Matt Cummins Triple: [Pat Cummins, hasSibling, Matt Cummins]
Generated description
Matt Cummins is an Australian man best known as the brother of international cricketer Pat Cummins.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Matt Cummins Target entity description: Matt Cummins is an Australian man best known as the brother of international cricketer Pat Cummins.
-
A.
Jeff Cummins
Jeff Cummins is an illustrator best known for his striking cover art on science fiction and fantasy publications, including numerous Doctor Who titles.
-
B.
Michael McCusker
Michael McCusker is an American film editor known for his work on major Hollywood productions, including the thriller "The Girl on the Train" (2016).
-
C.
Kevin McLaughlin
Kevin McLaughlin is a literary scholar and translator known for his English translation of Walter Benjamin’s "The Arcades Project."
-
D.
Christian McLaughlin
Christian McLaughlin is a television producer and writer known for his work on various comedy and genre projects, including the film "The Invisible Woman."
-
E.
Kevin Duggan
Kevin Duggan is a relatively obscure individual whose name is shared with multiple people across different professions, such as sports and public service.
- 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53b01331c8190bec3aba40358a843 |
completed | April 19, 2026, 8:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07c4dd20d88190bc3dc16062764414 |
completed | May 16, 2026, 1:14 a.m. |
| NEDg | Description generation | batch_6a07c5aea8948190b6e5bbcea8053478 |
completed | May 16, 2026, 1:17 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07c6846fb481908e1d5aae2c53a7ba |
completed | May 16, 2026, 1:21 a.m. |
Created at: April 10, 2026, 11:43 a.m.