Triple
T1359334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | W-3 Sokół |
E29061
|
entity |
| Predicate | variant |
P4680
|
FINISHED |
| Object | W-3P |
E29061
|
NE 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: W-3P | Statement: [W-3 Sokół, variant, W-3P]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: W-3P Context triple: [W-3 Sokół, variant, W-3P]
-
A.
W3
W3 is a common shorthand for the World Wide Web, the global system of interlinked hypertext documents and resources accessed via the internet.
-
B.
WPK
WPK is the ruling communist party of North Korea that dominates the country’s political system and state ideology.
-
C.
W8
W8 is a central London postcode district covering the affluent Kensington area, known for its upscale residences, shops, and cultural institutions.
-
D.
WCP
WCP is the abbreviation for the World Climate Programme, an international initiative focused on understanding and addressing global climate variability and change.
-
E.
W-3 Sokół
chosen
The W-3 Sokół is a Polish multi-purpose medium helicopter widely used for transport, search and rescue, and military operations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a498d77abc8190913bf57e5f51d2c4 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c290db288190910fcfa17e902663 |
completed | March 1, 2026, 10:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acce725fec819085f6de8e6e368aa4 |
completed | March 8, 2026, 1:18 a.m. |
Created at: March 1, 2026, 7:56 p.m.