Triple
T37454726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Fourth Protocol |
E930765
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object |
Marble Arch Productions
Marble Arch Productions is a film and television production company known for producing works such as the Cold War thriller "The Fourth Protocol."
|
E2226522
|
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: Marble Arch Productions | Statement: [The Fourth Protocol, productionCompany, Marble Arch Productions]
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: Marble Arch Productions Triple: [The Fourth Protocol, productionCompany, Marble Arch Productions]
Generated description
Marble Arch Productions is a film and television production company known for producing works such as the Cold War thriller "The Fourth Protocol."
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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8e0ce590819087434d4ecc6f50da |
completed | May 6, 2026, 6:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40826588348190a9a7f0a0edf1b210 |
completed | June 28, 2026, 2:09 a.m. |
| NEDg | Description generation | batch_6a4083266990819092378557ff164ce0 |
completed | June 28, 2026, 2:12 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a4083cb3a90819082ec8d56067094a0 |
completed | June 28, 2026, 2:15 a.m. |
Created at: May 3, 2026, 4:17 p.m.