Triple
T20699113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Hanover |
E508730
|
entity |
| Predicate | primaryWeapon |
P6066
|
FINISHED |
| Object | Saber |
—
|
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: Saber | Statement: [Battle of Hanover, primaryWeapon, Saber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saber Context triple: [Battle of Hanover, primaryWeapon, Saber]
-
A.
Saber
chosen
Saber is a central heroic spirit and skilled swordswoman in the Fate/stay night: Unlimited Blade Works anime, known for her noble demeanor, chivalry, and iconic Excalibur.
-
B.
Sifa
Sifa is a German train safety system that monitors driver alertness and automatically intervenes if the driver fails to respond.
-
C.
Chain Sword
Chain Sword is a retractable, chain-linked blade weapon used by the Jaeger Gipsy Danger in the Pacific Rim universe for close-quarters combat against kaiju.
-
D.
Espada
Espada is a Spanish-origin surname borne by various notable individuals in sports, politics, and the arts.
-
E.
Espada
Espada is the charismatic lead male toreador character in the ballet Don Quixote, known for his bravura dancing and swaggering, heroic presence.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4c2b2a481909e31e9cb8f81ab55 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c113e4cc8190aabc11e3f2530e32 |
completed | April 21, 2026, 12:13 a.m. |
Created at: April 16, 2026, 12:11 p.m.