Triple
T14691338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Army of the Dead |
E345041
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Shay Hatten |
E331513
|
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: Shay Hatten | Statement: [Army of the Dead, writer, Shay Hatten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shay Hatten Context triple: [Army of the Dead, writer, Shay Hatten]
-
A.
Shay Hatten
chosen
Shay Hatten is an American screenwriter known for his work on high-octane action films, including entries in the John Wick franchise.
-
B.
Shay Haley
Shay Haley is an American musician, producer, and member of the band N.E.R.D., known for his long-time collaboration with Pharrell Williams.
-
C.
Shayna Saide
Shayna Saide is an American visual artist and former dancer best known as the mother of actor Shia LaBeouf.
-
D.
Shay Mooney
Shay Mooney is an American country-pop singer and songwriter best known as one half of the Grammy-winning duo Dan + Shay.
-
E.
Riley Shanahan
Riley Shanahan is an American actor and performer best known for physically portraying Robotman in the television series "Doom Patrol."
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb585d46c81908d6964130914cec4 |
completed | April 14, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde18b4bdc8190b5daf05484de7cd8 |
completed | May 8, 2026, 1:13 p.m. |
Created at: April 10, 2026, 1:28 a.m.