Triple
T29269240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Centaur T |
E742064
|
entity |
| Predicate | separationStage |
P120770
|
FINISHED |
| Object | mounted atop Titan IV core stage |
—
|
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: mounted atop Titan IV core stage | Statement: [Centaur T, separationStage, mounted atop Titan IV core stage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: separationStage Context triple: [Centaur T, separationStage, mounted atop Titan IV core stage]
-
A.
separationPhase
chosen
Indicates the phase or stage during which two previously connected entities are being separated or detached from one another.
-
B.
separationProcess
Indicates a process in which components of a mixture or system are divided or isolated from one another based on differing properties or conditions.
-
C.
separatesPhase
Indicates that one entity causes or defines a division between different phases or states of another entity or process.
-
D.
separationMethod
Indicates the technique or process used to separate one substance, component, or entity from another.
-
E.
typeOfSeparation
Indicates the specific manner or category of separation that exists or occurred between entities.
- 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_69f0912124d48190a046642b69407f4c |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 28, 2026, 12:47 p.m.