Triple
T34216017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Florida Flight 90 crash |
E877789
|
entity |
| Predicate | notableRescuer |
P99414
|
FINISHED |
| Object |
Lenny Skutnik
Lenny Skutnik is a former U.S. government employee best known for heroically diving into the icy Potomac River to save a passenger during the 1982 Air Florida Flight 90 crash, an act for which he was honored at President Reagan’s State of the Union address.
|
E2085470
|
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: Lenny Skutnik | Statement: [Air Florida Flight 90 crash, notableRescuer, Lenny Skutnik]
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: Lenny Skutnik Triple: [Air Florida Flight 90 crash, notableRescuer, Lenny Skutnik]
Generated description
Lenny Skutnik is a former U.S. government employee best known for heroically diving into the icy Potomac River to save a passenger during the 1982 Air Florida Flight 90 crash, an act for which he was honored at President Reagan’s State of the Union address.
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_69f349b0b4bc819088c1552424089ee9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7107e66e88190a799e0c78f1af117 |
completed | May 3, 2026, 9:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36cc936cd48190a00dcc1e25c73735 |
completed | June 20, 2026, 5:23 p.m. |
| NEDg | Description generation | batch_6a36cd459d308190b392db0c0f0a6a0a |
completed | June 20, 2026, 5:26 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a36cdcfa9048190a616290bd685e0d3 |
completed | June 20, 2026, 5:28 p.m. |
Created at: May 1, 2026, 1:55 a.m.