Triple
T32075075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Falcon 9 transporter-erector |
E819120
|
entity |
| Predicate | movementOrientation |
P167376
|
FINISHED |
| Object | horizontal during transport |
—
|
LITERAL 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: horizontal during transport | Statement: [Falcon 9 transporter-erector, movementOrientation, horizontal during transport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: movementOrientation Context triple: [Falcon 9 transporter-erector, movementOrientation, horizontal during transport]
-
A.
movementDirection
Indicates the direction or path along which an entity moves or is moving relative to a reference frame or point.
-
B.
movementDescriptor
chosen
Indicates how an entity moves or the manner in which its movement is characterized in relation to another entity or context.
-
C.
movementLocation
Indicates a relationship where an entity moves to, from, or through a specified location.
-
D.
movementRole
Indicates the specific function or capacity an entity has within a movement or motion-related activity (e.g., mover, path, source, or goal).
-
E.
locationOrientation
Indicates how one entity is spatially oriented or positioned relative to a specific location or reference point.
- F. None of above.
Provenance (3 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_69f348ff8ef88190931c08ba530a36bc |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6f38159d08190980ad639e08f00f4 |
completed | May 3, 2026, 7:04 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d7bee48190b94e0beb48a1d7fa |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 12:23 a.m.