Triple
T23349083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kubo and the Two Strings |
E591956
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Marc Haimes
Marc Haimes is a screenwriter and former studio executive best known for co-writing the acclaimed animated fantasy film "Kubo and the Two Strings."
|
E1586408
|
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: Marc Haimes | Statement: [Kubo and the Two Strings, screenwriter, Marc Haimes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marc Haimes Context triple: [Kubo and the Two Strings, screenwriter, Marc Haimes]
-
A.
Michael Haussman
Michael Haussman is an American director and filmmaker best known for his work on high-profile music videos and commercials.
-
B.
Marc Zamarin
Marc Zamarin is a sports executive best known for serving as the general manager of the Philadelphia Wings professional lacrosse team.
-
C.
Uriel Frisch
Uriel Frisch is a French physicist and mathematician renowned for his contributions to fluid dynamics and turbulence theory.
-
D.
Marc Roskin
Marc Roskin is a television producer and director best known for his work on genre and adventure series such as "The Librarians."
-
E.
Andrew Mondshein
Andrew Mondshein is an American film editor known for his work on acclaimed movies such as "Ma Rainey's Black Bottom" and "The Sixth Sense."
- 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: Marc Haimes Triple: [Kubo and the Two Strings, screenwriter, Marc Haimes]
Generated description
Marc Haimes is a screenwriter and former studio executive best known for co-writing the acclaimed animated fantasy film "Kubo and the Two Strings."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marc Haimes Target entity description: Marc Haimes is a screenwriter and former studio executive best known for co-writing the acclaimed animated fantasy film "Kubo and the Two Strings."
-
A.
Michael Haussman
Michael Haussman is an American director and filmmaker best known for his work on high-profile music videos and commercials.
-
B.
Marc Zamarin
Marc Zamarin is a sports executive best known for serving as the general manager of the Philadelphia Wings professional lacrosse team.
-
C.
Uriel Frisch
Uriel Frisch is a French physicist and mathematician renowned for his contributions to fluid dynamics and turbulence theory.
-
D.
Marc Roskin
Marc Roskin is a television producer and director best known for his work on genre and adventure series such as "The Librarians."
-
E.
Andrew Mondshein
Andrew Mondshein is an American film editor known for his work on acclaimed movies such as "Ma Rainey's Black Bottom" and "The Sixth Sense."
- 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_69e25d20e3d08190bcede87673cafb25 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f199cb2a3c8190a5c0c8d8735256c7 |
completed | April 29, 2026, 5:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c6784d6848190b232ae6366430c88 |
completed | May 19, 2026, 1:37 p.m. |
| NEDg | Description generation | batch_6a0c7213e19881909151fe5c0560e096 |
completed | May 19, 2026, 2:22 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c76ed37b08190af81b4ae2dc7c028 |
completed | May 19, 2026, 2:42 p.m. |
Created at: April 17, 2026, 5:19 p.m.