Triple
T6889512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glengarry Glen Ross |
E159008
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Dave Moss
Dave Moss is a disgruntled, scheming real estate salesman in "Glengarry Glen Ross" who plots to steal valuable leads from his own firm.
|
E627632
|
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: Dave Moss | Statement: [Glengarry Glen Ross, character, Dave Moss]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dave Moss Context triple: [Glengarry Glen Ross, character, Dave Moss]
-
A.
Pat Moss
Pat Moss was a pioneering British rally driver and equestrian, renowned as one of the most successful women in international motorsport during the mid-20th century.
-
B.
Dan Mott
Dan Mott is a fictional character portrayed as a cautious, neurotic member of the central trio in the 2004 adventure comedy film "Without a Paddle."
-
C.
Mike Mosley
Mike Mosley is an American hip-hop record producer known for his work with prominent West Coast rap artists in the 1990s.
-
D.
Steve Mason
Steve Mason is a cinematographer known for his work on feature films, including the crime thriller "The Bag Man."
-
E.
Scott Mosier
Scott Mosier is a Canadian-American film producer, editor, and podcaster best known for his longtime collaboration with filmmaker Kevin Smith on movies such as "Clerks" and "Dogma."
- 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: Dave Moss Triple: [Glengarry Glen Ross, character, Dave Moss]
Generated description
Dave Moss is a disgruntled, scheming real estate salesman in "Glengarry Glen Ross" who plots to steal valuable leads from his own firm.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dave Moss Target entity description: Dave Moss is a disgruntled, scheming real estate salesman in "Glengarry Glen Ross" who plots to steal valuable leads from his own firm.
-
A.
Pat Moss
Pat Moss was a pioneering British rally driver and equestrian, renowned as one of the most successful women in international motorsport during the mid-20th century.
-
B.
Dan Mott
Dan Mott is a fictional character portrayed as a cautious, neurotic member of the central trio in the 2004 adventure comedy film "Without a Paddle."
-
C.
Mike Mosley
Mike Mosley is an American hip-hop record producer known for his work with prominent West Coast rap artists in the 1990s.
-
D.
Steve Mason
Steve Mason is a cinematographer known for his work on feature films, including the crime thriller "The Bag Man."
-
E.
Scott Mosier
Scott Mosier is a Canadian-American film producer, editor, and podcaster best known for his longtime collaboration with filmmaker Kevin Smith on movies such as "Clerks" and "Dogma."
- 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_69c6883568c8819081db6407e892cccc |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d9117c84819093dad7b765337b63 |
completed | March 27, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c748cc2f908190b593cd82133a7b16 |
completed | March 28, 2026, 3:19 a.m. |
| NEDg | Description generation | batch_69c749d4b088819095f991f976592d04 |
completed | March 28, 2026, 3:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c74aab12988190bd23cfcc06c55cde |
completed | March 28, 2026, 3:27 a.m. |
Created at: March 27, 2026, 2:23 p.m.