Triple
T25641815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BE-3 engine |
E642855
|
entity |
| Predicate | firstFlightProgram |
P191956
|
FINISHED |
| Object | Blue Origin New Shepard program |
—
|
NE NERFINISHED |
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: Blue Origin New Shepard program | Statement: [BE-3 engine, firstFlightProgram, Blue Origin New Shepard program]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstFlightProgram Context triple: [BE-3 engine, firstFlightProgram, Blue Origin New Shepard program]
-
A.
firstFlight
Indicates that the associated event or record corresponds to the earliest or initial flight taken or performed by the referenced entity.
-
B.
firstFlightType
Indicates the category or nature of an entity’s initial flight (e.g., test, commercial, cargo, passenger).
-
C.
firstFlightPeriod
Indicates the time period during which an entity’s first flight or initial airborne operation took place.
-
D.
firstFlightCommander
Indicates that one entity served as the first commander in charge of another entity’s inaugural flight.
-
E.
firstModelToFly
Indicates that the subject is the earliest or original model among a set that successfully achieved flight.
- F. None of above. chosen
Provenance (4 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_69e77e7ce28081908b08d65ee6e5c8be |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69fcf1b3d9a08190850b388308656266 |
completed | May 7, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69fcf0226d8c8190b23dceafb1794995 |
completed | May 7, 2026, 8:03 p.m. |
| PDg | Predicate description generation | batch_69fcf1b241888190a243f07051c71383 |
completed | May 7, 2026, 8:10 p.m. |
Created at: April 21, 2026, 5:44 p.m.