Triple
T36578842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soyuz 5 |
E902332
|
entity |
| Predicate | reentryAnomaly |
P174016
|
FINISHED |
| Object | service module failed to separate on first attempt |
—
|
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: service module failed to separate on first attempt | Statement: [Soyuz 5, reentryAnomaly, service module failed to separate on first attempt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reentryAnomaly Context triple: [Soyuz 5, reentryAnomaly, service module failed to separate on first attempt]
-
A.
reentryConcern
chosen
Indicates a concern or issue related to an entity’s return or reentry into a system, environment, or context after having been outside it.
-
B.
reentryCause
Indicates the factor, event, or condition that led to or triggered a reentry.
-
C.
reentryOutcome
Indicates the result or consequences of an entity’s return or reentry into a system, place, or context.
-
D.
reentryControl
Indicates that an entity manages or regulates the process of returning or re-entering into a system, environment, or state.
-
E.
reentryRecovery
Indicates the process or capability of safely recovering an object or vehicle after it reenters an atmosphere from space or high-altitude flight.
- 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_69f76e64d8908190868473959a250b94 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.