Triple
T19013634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sage Group |
E465288
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object |
David Goldman
David Goldman was a British entrepreneur best known for co-founding the accounting software company Sage Group and helping to build it into a global business.
|
E1371722
|
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: David Goldman | Statement: [Sage Group, founder, David Goldman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Goldman Context triple: [Sage Group, founder, David Goldman]
-
A.
Gary Goldman
Gary Goldman is an American screenwriter best known for his work on major science fiction and action films, including the 1990 movie "Total Recall."
-
B.
Gary Goldman
Gary Goldman is an American animator, director, and producer best known for his work on Don Bluth–style animated films such as Anastasia.
-
C.
Martin Goldstein
Martin Goldstein, nicknamed "Buggsy," was an American mobster and hitman associated with Murder, Inc. during the 1930s and 1940s.
-
D.
Andrew Goldman
Andrew Goldman is a film editor known for his work on the independent feature "Tiny Furniture."
-
E.
Len Goldstein
Len Goldstein is a television producer known for his executive production work on series such as "The Astronaut Wives Club."
- 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: David Goldman Triple: [Sage Group, founder, David Goldman]
Generated description
David Goldman was a British entrepreneur best known for co-founding the accounting software company Sage Group and helping to build it into a global business.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: David Goldman Target entity description: David Goldman was a British entrepreneur best known for co-founding the accounting software company Sage Group and helping to build it into a global business.
-
A.
Gary Goldman
Gary Goldman is an American animator, director, and producer best known for his work on Don Bluth–style animated films such as Anastasia.
-
B.
Gary Goldman
Gary Goldman is an American screenwriter best known for his work on major science fiction and action films, including the 1990 movie "Total Recall."
-
C.
Martin Goldstein
Martin Goldstein, nicknamed "Buggsy," was an American mobster and hitman associated with Murder, Inc. during the 1930s and 1940s.
-
D.
Andrew Goldman
Andrew Goldman is a film editor known for his work on the independent feature "Tiny Furniture."
-
E.
Len Goldstein
Len Goldstein is a television producer known for his executive production work on series such as "The Astronaut Wives Club."
- 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_69d8dd025c188190a1d81f5b4ec7e2c6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6aac4dc8190ac51f22c13f1b96c |
completed | April 20, 2026, 7:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0723f372908190a8cb204e1bbe910c |
completed | May 15, 2026, 1:47 p.m. |
| NEDg | Description generation | batch_6a07257b21dc81908be073c286c3d3cb |
completed | May 15, 2026, 1:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07268dfaf88190ae8f93dbdbccdb5d |
completed | May 15, 2026, 1:58 p.m. |
Created at: April 10, 2026, 12:02 p.m.