Triple
T30835083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Thousand Plane Raid |
E785337
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Harold Goldman
Harold Goldman was a film producer known for his work on the World War II aviation movie "The Thousand Plane Raid."
|
E1943536
|
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: Harold Goldman | Statement: [The Thousand Plane Raid, producer, Harold Goldman]
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: Harold Goldman Triple: [The Thousand Plane Raid, producer, Harold Goldman]
Generated description
Harold Goldman was a film producer known for his work on the World War II aviation movie "The Thousand Plane Raid."
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_69f224b73d8c81908129383bfb397c87 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6913e2084819097d8df90d58ad26e |
completed | May 3, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a291817cf8481909bd8630a673e59b0 |
completed | June 10, 2026, 7:53 a.m. |
| NEDg | Description generation | batch_6a2919daa69c81908b00e106b009879b |
completed | June 10, 2026, 8:01 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a291b662b7c8190ba3db4db056351e1 |
completed | June 10, 2026, 8:08 a.m. |
Created at: April 29, 2026, 8:45 p.m.