Triple
T22968569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaidu |
E571117
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Kaidu |
—
|
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: Kaidu | Statement: [Kaidu, givenName, Kaidu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaidu Context triple: [Kaidu, givenName, Kaidu]
-
A.
Kaidu
chosen
Kaidu was a 13th-century Mongol prince and powerful rival of Kublai Khan who led prolonged resistance against the Yuan dynasty in Central Asia.
-
B.
Da Khüree
Da Khüree, also known as Örgöö, was the historical mobile capital and major monastic center of Outer Mongolia that evolved into present-day Ulaanbaatar.
-
C.
Shishkat
Shishkat is a village in the Hunza Valley of Gilgit-Baltistan, northern Pakistan, known for its proximity to the scenic Attabad Lake and the Karakoram Highway.
-
D.
Aimaq
Aimaq are a Persian-speaking, traditionally semi-nomadic ethnic group primarily inhabiting western and central Afghanistan and parts of eastern Iran.
-
E.
Sarlamkai
Sarlamkai is a traditional Mizo war dance characterized by vigorous movements that depict battle scenes and warrior spirit.
- 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_69e245b2c6548190a0e4c7f2f7df2d48 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182301f388190bb39e3d5b356dc65 |
completed | April 29, 2026, 3:59 a.m. |
Created at: April 17, 2026, 3:48 p.m.