Triple
T3854041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Guards of Finland |
E85366
|
entity |
| Predicate | leader |
P981
|
FINISHED |
| Object | Eero Haapalainen |
E98447
|
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: Eero Haapalainen | Statement: [Red Guards of Finland, leader, Eero Haapalainen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eero Haapalainen Context triple: [Red Guards of Finland, leader, Eero Haapalainen]
-
A.
Eero Haapalainen
chosen
Eero Haapalainen was a Finnish socialist politician and military leader who served as the commander-in-chief of the Red Guards during the Finnish Civil War.
-
B.
Tapio Wirkkala
Tapio Wirkkala was a renowned Finnish designer and sculptor celebrated for his influential work in glass, industrial design, and modern Finnish aesthetics.
-
C.
Hannu Heikkinen
Hannu Heikkinen is a structural engineer known for his work on the design and construction of Toronto City Hall.
-
D.
Timo Toikkanen
Timo Toikkanen is a technology executive known for his leadership roles at Microsoft Mobile and in the broader mobile and software industries.
-
E.
Heikki Mannila
Heikki Mannila is a Finnish computer scientist known for his influential research in data mining and machine learning, including foundational work on pattern discovery and exploratory data analysis.
- 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_69aed936de1c81908f91bed80f70abb2 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec0438308190865ff74bee5a1cf2 |
completed | March 9, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5041c7250819093b2743afeb6e36c |
completed | March 14, 2026, 6:45 a.m. |
Created at: March 9, 2026, 3:19 p.m.