Triple
T28932939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heinkel He 162 |
E733835
|
entity |
| Predicate | intendedToSupplement |
P93862
|
FINISHED |
| Object | Messerschmitt Me 262 |
—
|
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: Messerschmitt Me 262 | Statement: [Heinkel He 162, intendedToSupplement, Messerschmitt Me 262]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedToSupplement Context triple: [Heinkel He 162, intendedToSupplement, Messerschmitt Me 262]
-
A.
designedToSupplement
chosen
Indicates that one entity is created or intended to enhance, complete, or add to the function, content, or effect of another entity.
-
B.
hasSupplement
Indicates that one entity provides or is associated with an additional supporting or enhancing item, resource, or component for another entity.
-
C.
intendedWith
Indicates that one entity is the planned or desired target, recipient, or context for the use or application of another entity.
-
D.
isIntendedToSupport
Indicates that one entity is designed or purposed to provide assistance, reinforcement, or backing to another entity or activity.
-
E.
plannedComplement
Indicates that one entity is intentionally designed or arranged to complete, enhance, or work in coordination with another as part of a planned relationship.
- 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_69f05b0b49b08190b8994b339c7980f6 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f7675b12848190a3569cfda29c5b0e |
completed | May 3, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69f762f4b59481909f70074f11825bfb |
completed | May 3, 2026, 3 p.m. |
Created at: April 28, 2026, 8:29 a.m.