Triple
T33106421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMS Leipzig |
E847200
|
entity |
| Predicate | commanderDuringWWI |
P43732
|
FINISHED |
| Object | Kapitän zur See Haun (early war) |
—
|
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: Kapitän zur See Haun (early war) | Statement: [SMS Leipzig, commanderDuringWWI, Kapitän zur See Haun (early war)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commanderDuringWWI Context triple: [SMS Leipzig, commanderDuringWWI, Kapitän zur See Haun (early war)]
-
A.
commanderDuringWorldWarII
Indicates that one entity served as a commander of the other specifically during the period of World War II.
-
B.
roleInWorldWarI
chosen
Indicates the specific function, position, or involvement an entity had during World War I.
-
C.
higherCommandDuringWWII
Indicates that one entity served as the superior military authority or command over another entity during World War II.
-
D.
commanderInChiefDuringWar
Indicates that one entity served as the highest-ranking military leader (commander in chief) of another entity for the duration of a specified war.
-
E.
operatorDuringWorldWarII
Indicates that an entity operated or was active in its role during the period of World War II.
- 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_69f3495686508190b76bf20fa5e00bf7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
Created at: May 1, 2026, 1:26 a.m.