Triple

T11544125
Position Surface form Disambiguated ID Type / Status
Subject Zerg E273739 entity
Predicate unitProductionStructure P99979 FINISHED
Object Hive
The Hive is the Zerg’s ultimate tech structure in StarCraft, enabling advanced units, upgrades, and late-game capabilities.
E930817 NE FINISHED

How this triple was built (4 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: Hive | Statement: [Zerg, unitProductionStructure, Hive]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hive
Context triple: [Zerg, unitProductionStructure, Hive]
  • A. Apache Hive
    Apache Hive is a data warehouse and SQL-like query system built on top of Hadoop for managing and analyzing large datasets stored in distributed storage.
  • B. HiveQL
    HiveQL is a SQL-like query language designed for managing and analyzing large datasets stored in Apache Hive’s data warehouse system on Hadoop.
  • C. Hive Metastore
    Hive Metastore is a central metadata repository service that stores and manages schema and table information for data warehousing systems like Apache Hive.
  • D. HiveServer2
    HiveServer2 is a service component of Apache Hive that provides a secure, multi-client, and concurrent interface for executing Hive queries.
  • E. IMPALA
    IMPALA is a scalable deep reinforcement learning architecture designed for efficient distributed training of agents across many tasks and environments.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Hive
Triple: [Zerg, unitProductionStructure, Hive]
Generated description
The Hive is the Zerg’s ultimate tech structure in StarCraft, enabling advanced units, upgrades, and late-game capabilities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hive
Target entity description: The Hive is the Zerg’s ultimate tech structure in StarCraft, enabling advanced units, upgrades, and late-game capabilities.
  • A. Apache Hive
    Apache Hive is a data warehouse and SQL-like query system built on top of Hadoop for managing and analyzing large datasets stored in distributed storage.
  • B. HiveQL
    HiveQL is a SQL-like query language designed for managing and analyzing large datasets stored in Apache Hive’s data warehouse system on Hadoop.
  • C. Hive Metastore
    Hive Metastore is a central metadata repository service that stores and manages schema and table information for data warehousing systems like Apache Hive.
  • D. HiveServer2
    HiveServer2 is a service component of Apache Hive that provides a secure, multi-client, and concurrent interface for executing Hive queries.
  • E. IMPALA
    IMPALA is a scalable deep reinforcement learning architecture designed for efficient distributed training of agents across many tasks and environments.
  • F. None of above. chosen

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_69d6aae4dfa48190a3ab0b19a159a3c5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d886e1d754819089f3b6be3404fa0b completed April 10, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69e685cc855881908ea96d84c76e3a4d completed April 20, 2026, 8 p.m.
NEDg Description generation batch_69e68fd9d1b88190ba6057a52f51c961 completed April 20, 2026, 8:43 p.m.
NED2 Entity disambiguation (via description) batch_69e69f3de9208190b65f25c3e2d6e222 completed April 20, 2026, 9:48 p.m.
Created at: April 8, 2026, 9:37 p.m.