Triple

T27591621
Position Surface form Disambiguated ID Type / Status
Subject TiKV E699798 entity
Predicate usesComponent P35 FINISHED
Object Placement Driver (PD)
Placement Driver (PD) is the central metadata and cluster management service in the TiKV/TiDB ecosystem, responsible for tasks like scheduling, load balancing, and maintaining data placement information.
E1779701 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: Placement Driver (PD) | Statement: [TiKV, usesComponent, Placement Driver (PD)]
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: Placement Driver (PD)
Triple: [TiKV, usesComponent, Placement Driver (PD)]
Generated description
Placement Driver (PD) is the central metadata and cluster management service in the TiKV/TiDB ecosystem, responsible for tasks like scheduling, load balancing, and maintaining data placement information.

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_69ef6a4d71f081909a1235763206b691 completed April 27, 2026, 1:53 p.m.
NER Named-entity recognition batch_69f63054e1108190af382cc66b756401 completed May 2, 2026, 5:11 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12d0de87648190af1f77af5236da80 completed May 24, 2026, 10:20 a.m.
NEDg Description generation batch_6a12d169e8888190bf3c8e7f0718a3a5 completed May 24, 2026, 10:22 a.m.
NED2 Entity disambiguation (via description) batch_6a12d270e0dc81909c04761a32c1e652 completed May 24, 2026, 10:26 a.m.
Created at: April 27, 2026, 2:05 p.m.