Triple
T25488722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shutter (2008 film) |
E638781
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Luke Dawson
Luke Dawson is an American screenwriter best known for writing the horror film "Shutter" (2008) and contributing to other genre projects in film and television.
|
E1685542
|
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: Luke Dawson | Statement: [Shutter (2008 film), screenwriter, Luke Dawson]
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: Luke Dawson Triple: [Shutter (2008 film), screenwriter, Luke Dawson]
Generated description
Luke Dawson is an American screenwriter best known for writing the horror film "Shutter" (2008) and contributing to other genre projects in film and television.
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_69e75dbabeac8190bab30628f8b799d4 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f7a205688190b8f36bff5013247c |
completed | May 2, 2026, 1:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a10b73db5f08190807cd7ced554b2e5 |
completed | May 22, 2026, 8:06 p.m. |
| NEDg | Description generation | batch_6a10b7d88f6c8190a73108b86191ea5d |
completed | May 22, 2026, 8:08 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a10b91b5be08190a85532fe02db813e |
completed | May 22, 2026, 8:14 p.m. |
Created at: April 21, 2026, 2:34 p.m.