Triple
T32766384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SP5 (civilian variant) |
E837912
|
entity |
| Predicate | sharesAppearanceWith |
P71318
|
FINISHED |
| Object | Heckler & Koch MP5 |
—
|
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: Heckler & Koch MP5 | Statement: [SP5 (civilian variant), sharesAppearanceWith, Heckler & Koch MP5]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesAppearanceWith Context triple: [SP5 (civilian variant), sharesAppearanceWith, Heckler & Koch MP5]
-
A.
sharesAppearanceTraitWith
chosen
Indicates that two entities possess at least one similar or matching visual or appearance-related characteristic.
-
B.
sharesWith
Indicates that one entity gives another entity access to or use of something it possesses.
-
C.
sharesUniverseWith
Indicates that two entities exist within the same fictional or narrative universe, implying shared continuity, setting, or canon.
-
D.
sharesAreaWith
Indicates that two entities occupy or overlap the same geographic or spatial area.
-
E.
sharesFieldWith
Indicates that two entities are involved in or associated with the same field, discipline, or area of specialization.
- 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_69f34939857c8190aa9970c51feec1eb |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69ff79e7206c8190a809b5f2a6261378 |
completed | May 9, 2026, 6:16 p.m. |
| PD | Predicate disambiguation | batch_69ff798356b881908645074fb3a96517 |
completed | May 9, 2026, 6:14 p.m. |
Created at: May 1, 2026, 1:13 a.m.