Triple
T19763018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Handschar |
E474677
|
entity |
| Predicate | isRelatedTo |
P37
|
FINISHED |
| Object | Scimitar |
—
|
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: Scimitar | Statement: [Handschar, isRelatedTo, Scimitar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scimitar Context triple: [Handschar, isRelatedTo, Scimitar]
-
A.
Scimitar
chosen
Scimitar is a type of curved, single-edged sword traditionally associated with Middle Eastern, South Asian, and North African cultures.
-
B.
Assegai
Assegai is an adventure novel by Wilbur Smith in the Courtney series, set in early 20th-century East Africa and centered on big-game hunting, espionage, and the buildup to World War I.
-
C.
Talwara
Talwara is a small town in the Indian state of Himachal Pradesh, known primarily for its proximity to the Pong Dam on the Beas River.
-
D.
Cawood Sword
The Cawood Sword is a remarkably well-preserved medieval Viking-age sword, renowned as one of the finest and most complete examples of its kind discovered in Britain.
-
E.
The Spear
The Spear is the nickname of the U.S. Air Force’s 53rd Wing, a unit known for operational testing and evaluation of advanced weapons and systems.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65320df3c8190b34f9908d5da48d9 |
completed | April 20, 2026, 4:24 p.m. |
Created at: April 10, 2026, 1:48 p.m.