Triple
T27687217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Porsche Tiger VK 45.01(P) |
E698063
|
entity |
| Predicate | chassisConvertedInto |
P66199
|
FINISHED |
| Object | Ferdinand tank destroyer |
—
|
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: Ferdinand tank destroyer | Statement: [Porsche Tiger VK 45.01(P), chassisConvertedInto, Ferdinand tank destroyer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chassisConvertedInto Context triple: [Porsche Tiger VK 45.01(P), chassisConvertedInto, Ferdinand tank destroyer]
-
A.
chassis
Indicates that one entity serves as the structural frame or supporting base (chassis) for another entity.
-
B.
usedChassisFor
chosen
Indicates that one entity employed or incorporated another entity’s chassis as the structural base or framework for its construction or operation.
-
C.
chassisConstruction
Indicates how the chassis of an object is built or assembled, specifying the construction method or structural design used.
-
D.
chassisOrigin
Indicates the place or source from which a chassis was originally produced, manufactured, or derived.
-
E.
chassisDesigner
Indicates that one entity is the designer or creator responsible for the chassis of another entity.
- 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_69ef590df8708190af5488f0638e790c |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63574d2388190839cd1061e3c9074 |
completed | May 2, 2026, 5:33 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:50 p.m.