Triple

T38378672
Position Surface form Disambiguated ID Type / Status
Subject Shibani Khan E893695 entity
Predicate battle P12 FINISHED
Object Battle of Merv
The Battle of Merv was a 1510 conflict in which the Safavid ruler Shah Ismail I decisively defeated and killed the Uzbek leader Muhammad Shaybani Khan, securing Khorasan for the Safavid Empire.
E2273398 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: Battle of Merv | Statement: [Shibani Khan, battle, Battle of Merv]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Battle of Merv
Triple: [Shibani Khan, battle, Battle of Merv]
Generated description
The Battle of Merv was a 1510 conflict in which the Safavid ruler Shah Ismail I decisively defeated and killed the Uzbek leader Muhammad Shaybani Khan, securing Khorasan for the Safavid Empire.

Provenance (5 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_69f76e4b1f748190a380696a16eae4a2 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69fcccfd753881908786a1c94efc4e9f completed May 7, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_6a41d63e4214819084453df734df02e2 completed June 29, 2026, 2:19 a.m.
NEDg Description generation batch_6a41d97e02608190872b043540e7ffa0 completed June 29, 2026, 2:33 a.m.
NED2 Entity disambiguation (via description) batch_6a41d9a93e4c81909feefea77ffb8d7e completed June 29, 2026, 2:34 a.m.
Created at: May 3, 2026, 4:31 p.m.