Triple
T9240112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Afghan invasions |
E222035
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Kerman |
E214530
|
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: Kerman | Statement: [Afghan invasions, location, Kerman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kerman Context triple: [Afghan invasions, location, Kerman]
-
A.
Kerman
chosen
Kerman is a major city in southeastern Iran known for its rich history, traditional bazaars, and proximity to desert landscapes.
-
B.
Kerman
Kerman is a small city in California’s San Joaquin Valley, known for its agricultural economy and location west of Fresno.
-
C.
Kerman
Kerman is the surname of Piper Kerman, the American author whose memoir inspired the television series "Orange Is the New Black."
-
D.
Birjand
Birjand is a city in eastern Iran that serves as the capital of South Khorasan Province and is known for its historical forts and saffron production.
-
E.
Yazd
Yazd is an ancient desert city in central Iran known for its well-preserved mud-brick architecture, Zoroastrian heritage, and historically significant Jewish community.
- 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_69ca83ee26cc81909ac624e190597d6d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccf0a3888c8190b72d8d0b850bdfbc |
completed | April 1, 2026, 10:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d87dfc46e08190bea27c11b987cb6d |
completed | April 10, 2026, 4:35 a.m. |
Created at: March 30, 2026, 7:30 p.m.