Triple
T13120094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Water Land |
E311697
|
entity |
| Predicate | hasNotableEnemy |
P26163
|
FINISHED |
| Object | Big Bertha |
E165838
|
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: Big Bertha | Statement: [Water Land, hasNotableEnemy, Big Bertha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Big Bertha Context triple: [Water Land, hasNotableEnemy, Big Bertha]
-
A.
Big Bertha howitzer
chosen
The Big Bertha howitzer was a massive German siege artillery piece used in World War I, renowned for its ability to destroy heavily fortified positions with long-range, high-caliber shells.
-
B.
Paris Gun
The Paris Gun was a long-range German artillery piece used in World War I to bombard Paris from unprecedented distances.
-
C.
Schwerer Gustav railway gun
The Schwerer Gustav railway gun was an enormous German World War II super-heavy artillery piece, one of the largest cannons ever built, designed to destroy heavily fortified targets.
-
D.
Long Lance
Long Lance is the Allied nickname for Japan’s Type 93 torpedo, a highly advanced and powerful World War II naval weapon renowned for its exceptional range and destructive capability.
-
E.
Haynrode
Haynrode is a small village in the German state of Thuringia.
- 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_69d806a9fe888190b081e2d9ea665d6c |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98bce3678819082a7aa1d83f20592 |
completed | April 10, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6e286de608190bf46af2eb656bb79 |
completed | May 3, 2026, 5:52 a.m. |
Created at: April 9, 2026, 9:06 p.m.