Triple
T17607709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Armstrong |
E428877
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Joe
Joe is the given name of Joe Armstrong, the computer scientist best known as the co-creator of the Erlang programming language.
|
E1278923
|
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: Joe | Statement: [Joe Armstrong, givenName, Joe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Context triple: [Joe Armstrong, givenName, Joe]
-
A.
Joe
Joe is a central character in the classic 1959 comedy film "Some Like It Hot," where he is one of two musicians who disguise themselves as women to escape mobsters.
-
B.
Joe
Joe is a notable artwork created by Japanese photographer and artist Hiroshi Sugimoto.
-
C.
Joe
Joe is the given name of Joe Oros, an American automobile designer best known for leading the design of the original Ford Mustang.
-
D.
Joe
Joe is a central immortal warrior in the film "The Old Guard," known for his deep bond with fellow immortal Nicky and his role in the covert team of centuries-old fighters.
-
E.
Joe
Joe is the given name of American actor Joe Spano, known for his roles in television series such as "Hill Street Blues" and "NCIS."
- 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: Joe Triple: [Joe Armstrong, givenName, Joe]
Generated description
Joe is the given name of Joe Armstrong, the computer scientist best known as the co-creator of the Erlang programming language.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Joe Target entity description: Joe is the given name of Joe Armstrong, the computer scientist best known as the co-creator of the Erlang programming language.
-
A.
Joe
Joe is the given name of American singer Billy Joe Royal, known for his pop and country hits in the 1960s and beyond.
-
B.
Joe
Joe is the given name of Joe Oros, an American automobile designer best known for leading the design of the original Ford Mustang.
-
C.
Joe
Joe is the given name of Joe Rohde, the renowned Walt Disney Imagineer known for leading the design of Disney’s Animal Kingdom and other major projects.
-
D.
Joe
Joe is the given name of Joe Nickell, an American investigator and author known for his work examining alleged paranormal and mysterious phenomena.
-
E.
Joe
Joe is the given name of British fantasy author Joe Abercrombie, known for his gritty, character-driven novels such as the First Law series.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c4d8374819097cb112fba405e77 |
completed | April 19, 2026, 5:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a020a8ed8d081908346127e09f39512 |
completed | May 11, 2026, 4:57 p.m. |
| NEDg | Description generation | batch_6a020bc148c88190b0a59366ed87012b |
completed | May 11, 2026, 5:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a020c2ee784819082c0bbf09c12813b |
completed | May 11, 2026, 5:04 p.m. |
Created at: April 10, 2026, 5:51 a.m.