Triple
T6669145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heinkel He 178 |
E151680
|
entity |
| Predicate | firstPublicDemonstrationAudience |
P52647
|
FINISHED |
| Object | officials of the German Air Ministry |
—
|
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: officials of the German Air Ministry | Statement: [Heinkel He 178, firstPublicDemonstrationAudience, officials of the German Air Ministry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstPublicDemonstrationAudience Context triple: [Heinkel He 178, firstPublicDemonstrationAudience, officials of the German Air Ministry]
-
A.
firstDemonstrated
Indicates that one entity was the earliest to show, prove, or exemplify a particular concept, method, or capability in relation to another entity or context.
-
B.
firstPerformance
Indicates that an entity marks the initial or debut performance of another entity, such as a work, artist, or production.
-
C.
introducedAsDemonstrator
Indicates that one entity is presented or identified to another entity specifically in the role of a demonstrator.
-
D.
unveiledInPresenceOf
chosen
Indicates that something was formally revealed or made public while specific other entities were present.
-
E.
firstRunViewership
Indicates the number of viewers who watched a program during its initial (first) broadcast or release.
- 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_69c687f71fc081909dbd45d6377f6045 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ce738fe88190a5557900efeec7ec |
completed | March 27, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69c6ad09974c81908784300ae218961f |
completed | March 27, 2026, 4:15 p.m. |
Created at: March 27, 2026, 2:02 p.m.