Triple

T3252698
Position Surface form Disambiguated ID Type / Status
Subject Zeppelin airships E68218 entity
Predicate notableModel P1503 FINISHED
Object LZ 70
LZ 70 was a German World War I-era Zeppelin airship used primarily for military reconnaissance and bombing missions.
 E341867 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: LZ 70 | Statement: [Zeppelin airships, notableModel, LZ 70]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LZ 70
Context triple: [Zeppelin airships, notableModel, LZ 70]
  • A. Lansen
    Lansen is the NATO reporting name for the Swedish Saab 32, a Cold War-era jet aircraft used primarily for attack and reconnaissance roles.
  • B. LZ
    LZ is the stock ticker symbol for The Lubrizol Corporation, a specialty chemicals company known for its lubricant additives and advanced materials.
  • C. Lakki
    Lakki is a coastal town and main port on the Greek island of Leros in the Dodecanese.
  • D. Lakka
    Lakka is a picturesque coastal village on the Greek island of Paxos, known for its sheltered bay, clear turquoise waters, and traditional Ionian architecture.
  • E. Martz
    Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
  • 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: LZ 70
Triple: [Zeppelin airships, notableModel, LZ 70]
Generated description
LZ 70 was a German World War I-era Zeppelin airship used primarily for military reconnaissance and bombing missions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LZ 70
Target entity description: LZ 70 was a German World War I-era Zeppelin airship used primarily for military reconnaissance and bombing missions.
  • A. Lansen
    Lansen is the NATO reporting name for the Swedish Saab 32, a Cold War-era jet aircraft used primarily for attack and reconnaissance roles.
  • B. LZ
    LZ is the stock ticker symbol for The Lubrizol Corporation, a specialty chemicals company known for its lubricant additives and advanced materials.
  • C. Lakki
    Lakki is a coastal town and main port on the Greek island of Leros in the Dodecanese.
  • D. Lakka
    Lakka is a picturesque coastal village on the Greek island of Paxos, known for its sheltered bay, clear turquoise waters, and traditional Ionian architecture.
  • E. Martz
    Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
  • 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_69ad858f74408190bcbd07f967cd7bd0 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaf440bb88190a2450405afae7f1f completed March 8, 2026, 5:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28ec4375881908d7f22ef4a80b60c completed March 12, 2026, 10 a.m.
NEDg Description generation batch_69b28fbaa3048190b42991ede51c6ca8 completed March 12, 2026, 10:04 a.m.
NED2 Entity disambiguation (via description) batch_69b2ab2315ec8190b27da4e41696a7e3 completed March 12, 2026, 12:01 p.m.
Created at: March 8, 2026, 3:09 p.m.