Triple
T4949480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoffrey de Havilland |
E111132
|
entity |
| Predicate | testPiloted |
P21221
|
FINISHED |
| Object | his own early aircraft designs |
—
|
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: his own early aircraft designs | Statement: [Geoffrey de Havilland, testPiloted, his own early aircraft designs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testPiloted Context triple: [Geoffrey de Havilland, testPiloted, his own early aircraft designs]
-
A.
testPilot
chosen
Indicates that an entity serves as a pilot responsible for testing and evaluating aircraft or related flight systems.
-
B.
pilotRun
Indicates that an entity conducts or participates in a preliminary or trial implementation of a process, system, or project to test and evaluate it before full-scale deployment.
-
C.
hasPilot
Indicates that an entity is operated or controlled by a specific pilot.
-
D.
testedFor
Indicates that an entity has been examined or analyzed to determine the presence, absence, or level of another specified entity or condition.
-
E.
trialMode
Indicates that an entity is operating in a temporary, limited-capability trial state rather than in full or permanent mode.
- 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_69bd441721cc819085c7e33fe0876818 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd7166bb6c8190a40775ac8bb723a8 |
completed | March 20, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69bd6c3aa1388190b3e0c8ee1ba1e4fa |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:31 p.m.