Triple
T16590846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steven Haft |
E403079
|
entity |
| Predicate | producerOf |
P490
|
FINISHED |
| Object | Toys |
E184601
|
NE FINISHED |
How this triple was built (2 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: Toys | Statement: [Steven Haft, producerOf, Toys]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Toys Context triple: [Steven Haft, producerOf, Toys]
-
A.
Toys
chosen
Toys is a 1992 fantasy comedy film directed by Barry Levinson, known for its whimsical visual style and satirical take on the military-industrial complex.
-
B.
Toy
Toy is an American punk rock band known for its energetic sound and contributions to the underground punk scene.
-
C.
Living Toys
Living Toys is a 1993 chamber orchestra work by British composer Thomas Adès, noted for its vivid, surreal sound world and virtuosic, theatrical writing.
-
D.
toys-to-life
Toys-to-life is a video game genre where physical collectible figures or toys are used to unlock and interact with digital content within the game.
-
E.
Tec Toy
Tec Toy is a Brazilian electronics and video game company best known for localizing, manufacturing, and popularizing Sega consoles and games in Brazil.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e359a012e081909a0604dde3c04bbb |
completed | April 18, 2026, 10:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a007da6d6f08190a8524b1c955b7c2e |
completed | May 10, 2026, 12:44 p.m. |
Created at: April 10, 2026, 5:16 a.m.