Triple

T5305708
Position Surface form Disambiguated ID Type / Status
Subject Battleship Cove E120096 entity
Predicate hasPart P35 FINISHED
Object PT-796
PT-796 is a preserved World War II-era U.S. Navy patrol torpedo boat on display as a museum vessel at Battleship Cove in Massachusetts.
 E510913 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: PT-796 | Statement: [Battleship Cove, hasPart, PT-796]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PT-796
Context triple: [Battleship Cove, hasPart, PT-796]
  • A. PH-07
    PH-07 is the ISO 3166-2 code assigned to the Central Visayas administrative region of the Philippines.
  • B. UP-78
    UP-78 is the vehicle registration code assigned to motor vehicles registered in Kanpur, Uttar Pradesh, India.
  • C. NP7
    NP7 is a UK postal district within the NP (Newport) postcode area, covering Abergavenny and surrounding parts of Monmouthshire in south-east Wales.
  • D. NM-79
    NM-79 is a model of electric multiple unit rolling stock used to operate services on Mexico City Metro Line 3.
  • E. MR-73
    MR-73 is a class of rubber-tired electric multiple unit trains used on the Montreal Metro system.
  • 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: PT-796
Triple: [Battleship Cove, hasPart, PT-796]
Generated description
PT-796 is a preserved World War II-era U.S. Navy patrol torpedo boat on display as a museum vessel at Battleship Cove in Massachusetts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PT-796
Target entity description: PT-796 is a preserved World War II-era U.S. Navy patrol torpedo boat on display as a museum vessel at Battleship Cove in Massachusetts.
  • A. PH-07
    PH-07 is the ISO 3166-2 code assigned to the Central Visayas administrative region of the Philippines.
  • B. UP-78
    UP-78 is the vehicle registration code assigned to motor vehicles registered in Kanpur, Uttar Pradesh, India.
  • C. NP7
    NP7 is a UK postal district within the NP (Newport) postcode area, covering Abergavenny and surrounding parts of Monmouthshire in south-east Wales.
  • D. NM-79
    NM-79 is a model of electric multiple unit rolling stock used to operate services on Mexico City Metro Line 3.
  • E. MR-73
    MR-73 is a class of rubber-tired electric multiple unit trains used on the Montreal Metro system.
  • 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_69bd44704be88190acdb2ac481b0ff55 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd851dd0d081909c0bf1423278ad8a completed March 20, 2026, 5:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf10f77b048190b8d3b39b900008d8 completed March 21, 2026, 9:43 p.m.
NEDg Description generation batch_69bf1186f1988190893e8d1af8623f6d completed March 21, 2026, 9:45 p.m.
NED2 Entity disambiguation (via description) batch_69bf1226ddd08190a39799fd0db58694 completed March 21, 2026, 9:48 p.m.
Created at: March 20, 2026, 1:53 p.m.