Triple
T25295734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casey Siemaszko |
E634212
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Breaking In (1989 film)
Breaking In (1989 film) is a 1989 crime-comedy film directed by Bill Forsyth and written by John Sayles, following an aging professional burglar who takes on a young protégé.
|
E1672944
|
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: Breaking In (1989 film) | Statement: [Casey Siemaszko, notableWork, Breaking In (1989 film)]
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: Breaking In (1989 film) Triple: [Casey Siemaszko, notableWork, Breaking In (1989 film)]
Generated description
Breaking In (1989 film) is a 1989 crime-comedy film directed by Bill Forsyth and written by John Sayles, following an aging professional burglar who takes on a young protégé.
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_69e75a9503d48190b80a005c6af0cb50 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48fd1d1c08190ba007255d4527a6d |
completed | May 1, 2026, 11:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a10680c2e988190a659e17d926eb35c |
completed | May 22, 2026, 2:28 p.m. |
| NEDg | Description generation | batch_6a106940a70c81909a15eb7e78b00f0a |
completed | May 22, 2026, 2:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a106a510e208190894bcbb3d36b92dd |
completed | May 22, 2026, 2:38 p.m. |
Created at: April 21, 2026, 1:22 p.m.