Triple
T31616684
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Ihnat |
E806775
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Angel in My Pocket
Angel in My Pocket is a 1969 American comedy film starring Andy Griffith as a small-town minister facing humorous challenges in his new parish.
|
E1968843
|
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: Angel in My Pocket | Statement: [Steve Ihnat, notableWork, Angel in My Pocket]
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: Angel in My Pocket Triple: [Steve Ihnat, notableWork, Angel in My Pocket]
Generated description
Angel in My Pocket is a 1969 American comedy film starring Andy Griffith as a small-town minister facing humorous challenges in his new parish.
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_69f348d61f2081908cad94bc9ffbb671 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a8aac01c8190bd3ae7bb98512259 |
completed | May 3, 2026, 1:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b5665438c8190a00dcee088497b4a |
completed | June 12, 2026, 12:44 a.m. |
| NEDg | Description generation | batch_6a2b582d76f48190a79f766548d7292e |
completed | June 12, 2026, 12:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2b58de3f5c819098fdc0a6922670a1 |
completed | June 12, 2026, 12:54 a.m. |
Created at: April 30, 2026, 10:39 p.m.