Triple
T37593887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MG 34 Panzerlauf |
E935327
|
entity |
| Predicate | hasFitting |
P83948
|
FINISHED |
| Object | tank mounting fittings |
—
|
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: tank mounting fittings | Statement: [MG 34 Panzerlauf, hasFitting, tank mounting fittings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFitting Context triple: [MG 34 Panzerlauf, hasFitting, tank mounting fittings]
-
A.
fittedWith
chosen
Indicates that one entity is equipped, supplied, or provided with another entity as a component, feature, or accessory.
-
B.
hasGarment
Indicates that one entity possesses, wears, or is associated with a particular garment.
-
C.
fitsInto
Indicates that one entity can be placed inside another entity without exceeding its boundaries or capacity.
-
D.
fits
Indicates that one entity is appropriately sized, shaped, or otherwise suitable to be placed in, on, or together with another entity.
-
E.
hasSuit
Indicates that an entity possesses, wears, or is associated with a particular suit (such as clothing, armor, or a formal outfit).
- 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0062e6bd788190a7b4f3e5befb5cbb |
completed | May 10, 2026, 10:50 a.m. |
| PD | Predicate disambiguation | batch_6a0061989d188190b4815b2de3e8676f |
completed | May 10, 2026, 10:44 a.m. |
Created at: May 3, 2026, 4:18 p.m.