Triple

T22349069
Position Surface form Disambiguated ID Type / Status
Subject German destroyer Z31 E552477 entity
Predicate pennantNumber P3153 FINISHED
Object Z31
Z31 was a German Type 1936A (Mob) destroyer that served with the Kriegsmarine during World War II, participating in Arctic and Norwegian operations before being ceded to France as a war prize.
 E1532708 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: Z31 | Statement: [German destroyer Z31, pennantNumber, Z31]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Z31
Context triple: [German destroyer Z31, pennantNumber, Z31]
  • A. Z34
    Z34 is the internal chassis code used by Nissan to designate the 370Z sports car generation produced from 2009 onward.
  • B. Z3
    Z3 is a high-performance theorem prover and SMT (Satisfiability Modulo Theories) solver developed by Microsoft Research, widely used in formal verification, program analysis, and automated reasoning.
  • C. Z4
    Z4 was a German Kriegsmarine destroyer named Richard Beitzen that served during World War II in various North Sea and Atlantic operations.
  • D. Z-13
    Z-13 is the station code assigned to Kinshichō Station on Tokyo’s subway network.
  • E. Z6
    Z6 was the hull number of the German World War II destroyer Theodor Riedel, a Type 1934A-class vessel of the Kriegsmarine.
  • 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: Z31
Triple: [German destroyer Z31, pennantNumber, Z31]
Generated description
Z31 was a German Type 1936A (Mob) destroyer that served with the Kriegsmarine during World War II, participating in Arctic and Norwegian operations before being ceded to France as a war prize.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Z31
Target entity description: Z31 was a German Type 1936A (Mob) destroyer that served with the Kriegsmarine during World War II, participating in Arctic and Norwegian operations before being ceded to France as a war prize.
  • A. Z34
    Z34 is the internal chassis code used by Nissan to designate the 370Z sports car generation produced from 2009 onward.
  • B. Z3
    Z3 is a high-performance theorem prover and SMT (Satisfiability Modulo Theories) solver developed by Microsoft Research, widely used in formal verification, program analysis, and automated reasoning.
  • C. Z4
    Z4 was a German Kriegsmarine destroyer named Richard Beitzen that served during World War II in various North Sea and Atlantic operations.
  • D. Z-13
    Z-13 is the station code assigned to Kinshichō Station on Tokyo’s subway network.
  • E. Z6
    Z6 was the hull number of the German World War II destroyer Theodor Riedel, a Type 1934A-class vessel of the Kriegsmarine.
  • 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_69e11e4a0ad08190a385b4d343cf6524 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1579a1c308190ae2174f99ae317ab completed April 29, 2026, 12:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ae05844948190b13a0e927f2a1c1f completed May 18, 2026, 9:48 a.m.
NEDg Description generation batch_6a0ae2e2883c81908a6fea37f8db7f1a completed May 18, 2026, 9:58 a.m.
NED2 Entity disambiguation (via description) batch_6a0ae3855838819080bf6883946b62f7 completed May 18, 2026, 10:01 a.m.
Created at: April 16, 2026, 8:43 p.m.