Triple
T8604522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mera |
E203763
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object |
Andy Curry
Andy Curry is a fictional character in DC Comics, known as the son of Aquaman (Arthur Curry) and Mera.
|
E744972
|
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: Andy Curry | Statement: [Mera, relative, Andy Curry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andy Curry Context triple: [Mera, relative, Andy Curry]
-
A.
Adrian Curry
Adrian Curry is a film poster designer and curator known for his work highlighting and preserving classic and contemporary movie poster art.
-
B.
Darren Smyth
Darren Smyth is a European patent attorney and commentator known for his work in intellectual property law and contributions to patent-related scholarship and discussion.
-
C.
Stan Meads
Stan Meads was a New Zealand rugby union player and All Black lock, known both for his own strong international career and as the brother of legendary All Black Colin Meads.
-
D.
Tom Curry
Tom Curry was an English football trainer for Manchester United who died as a result of the 1958 Munich air disaster.
-
E.
Paul Durkan
Paul Durkan is an Irish poet known for his darkly comic, conversational verse that often explores family, politics, and contemporary Irish life.
- 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: Andy Curry Triple: [Mera, relative, Andy Curry]
Generated description
Andy Curry is a fictional character in DC Comics, known as the son of Aquaman (Arthur Curry) and Mera.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Andy Curry Target entity description: Andy Curry is a fictional character in DC Comics, known as the son of Aquaman (Arthur Curry) and Mera.
-
A.
Adrian Curry
Adrian Curry is a film poster designer and curator known for his work highlighting and preserving classic and contemporary movie poster art.
-
B.
Darren Smyth
Darren Smyth is a European patent attorney and commentator known for his work in intellectual property law and contributions to patent-related scholarship and discussion.
-
C.
Stan Meads
Stan Meads was a New Zealand rugby union player and All Black lock, known both for his own strong international career and as the brother of legendary All Black Colin Meads.
-
D.
Tom Curry
Tom Curry was an English football trainer for Manchester United who died as a result of the 1958 Munich air disaster.
-
E.
Paul Durkan
Paul Durkan is an Irish poet known for his darkly comic, conversational verse that often explores family, politics, and contemporary Irish life.
- 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_69ca832b56948190ba751cec255308f1 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc46dd8ff8819081ef269192047488 |
completed | March 31, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea8f8dfa4819080c8ed475a84be41 |
completed | April 2, 2026, 5:35 p.m. |
| NEDg | Description generation | batch_69cea9d0dad0819095134f6f8cafb4c0 |
completed | April 2, 2026, 5:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ceaa7025388190a3f17aca46d4858e |
completed | April 2, 2026, 5:42 p.m. |
Created at: March 30, 2026, 6:24 p.m.