Triple
T7786850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heinkel He 70 |
E187266
|
entity |
| Predicate | successorRoleInfluence |
P79009
|
FINISHED |
| Object | influenced later Heinkel bomber 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: influenced later Heinkel bomber designs | Statement: [Heinkel He 70, successorRoleInfluence, influenced later Heinkel bomber designs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorRoleInfluence Context triple: [Heinkel He 70, successorRoleInfluence, influenced later Heinkel bomber designs]
-
A.
successorRole
Indicates that one role or position directly follows and replaces another in a sequence or organizational structure.
-
B.
successorInSomeRoles
Indicates that one entity has taken over or followed another entity in certain specified roles or positions.
-
C.
successionRole
Indicates a role or position that one entity assumes as the successor to another in a sequence of holders or office-bearers.
-
D.
successorStateRole
Indicates that one role represents the state or position that directly follows and replaces another role in a sequence or process.
-
E.
successorInPractice
Indicates that one entity has taken over the role, position, or function of another in actual practice, even if not formally or officially designated as its successor.
- F. None of above. chosen
Provenance (4 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_69ca82af2d2c8190963861f5e0b8bf21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cae7e779ec8190b77296d9c2ac3210 |
completed | March 30, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69caa488532c819093ac40bba0b3c7ef |
completed | March 30, 2026, 4:27 p.m. |
| PDg | Predicate description generation | batch_69cae7e47c5c8190bca90d45b3cdc25e |
completed | March 30, 2026, 9:15 p.m. |
Created at: March 30, 2026, 4:24 p.m.