Triple
T18011408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treachery |
E430891
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object |
Matthew Ziff
Matthew Ziff is an American actor and producer known for his roles in independent films and genre movies.
|
E1302357
|
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: Matthew Ziff | Statement: [Treachery, hasCastMember, Matthew Ziff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matthew Ziff Context triple: [Treachery, hasCastMember, Matthew Ziff]
-
A.
Matthew Weisman
Matthew Weisman is a screenwriter best known for co-writing the 1985 action film "Commando" starring Arnold Schwarzenegger.
-
B.
Zachary Sklar
Zachary Sklar is an American screenwriter and journalist best known for co-writing Oliver Stone’s political thriller film "JFK."
-
C.
Zach Katz
Zach Katz is a music industry executive and producer known for his work with major artists and leadership roles at prominent record and publishing companies.
-
D.
Matthew Shafer
Matthew Shafer is an American writer known for his work on the animated series "Cowboy Bebop" and related projects.
-
E.
Matthew Shafer
Matthew Shafer, better known by his stage name Uncle Kracker, is an American singer-songwriter and musician recognized for his blend of rock, country, and pop influences.
- 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: Matthew Ziff Triple: [Treachery, hasCastMember, Matthew Ziff]
Generated description
Matthew Ziff is an American actor and producer known for his roles in independent films and genre movies.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Matthew Ziff Target entity description: Matthew Ziff is an American actor and producer known for his roles in independent films and genre movies.
-
A.
Matthew Weisman
Matthew Weisman is a screenwriter best known for co-writing the 1985 action film "Commando" starring Arnold Schwarzenegger.
-
B.
Zachary Sklar
Zachary Sklar is an American screenwriter and journalist best known for co-writing Oliver Stone’s political thriller film "JFK."
-
C.
Zach Katz
Zach Katz is a music industry executive and producer known for his work with major artists and leadership roles at prominent record and publishing companies.
-
D.
Matthew Shafer
Matthew Shafer is an American writer known for his work on the animated series "Cowboy Bebop" and related projects.
-
E.
Matthew Shafer
Matthew Shafer, better known by his stage name Uncle Kracker, is an American singer-songwriter and musician recognized for his blend of rock, country, and pop influences.
- 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b51fc108819089e6c130a89811bc |
completed | April 19, 2026, 10:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0349a6601c819080c973bb0d4af439 |
completed | May 12, 2026, 3:39 p.m. |
| NEDg | Description generation | batch_6a034bccb130819083c121e046eeb013 |
completed | May 12, 2026, 3:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a034c3e28508190b638984e08898ed5 |
completed | May 12, 2026, 3:50 p.m. |
Created at: April 10, 2026, 10:24 a.m.