Triple

T415445
Position Surface form Disambiguated ID Type / Status
Subject San Francisco Maritime National Historical Park E9581 entity
Predicate hasShip P14595 FINISHED
Object Alma
Alma is a historic wooden scow schooner preserved as a museum ship in San Francisco, representing the city’s 19th- and early 20th-century maritime commerce.
 E53488 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: Alma | Statement: [San Francisco Maritime National Historical Park, hasShip, Alma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Alma
Context triple: [San Francisco Maritime National Historical Park, hasShip, Alma]
  • A. Zella
    Zella is an activewear and athleisure clothing brand known for its performance-focused yet stylish designs, sold at Nordstrom.
  • B. Alva
    Alva is the middle name of the famed American inventor Thomas Edison, often used as part of his full name, Thomas Alva Edison.
  • C. Loralai
    Loralai is a town and district in northern Balochistan, Pakistan, known historically as a regional administrative and trade center.
  • D. Rebeca
    Rebeca is a feminine given name, commonly used in Spanish- and Portuguese-speaking countries, that is a variant of the name Rebecca.
  • E. Priscilla
    Priscilla is a feminine given name of Latin origin, commonly used in English-speaking countries.
  • 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: Alma
Triple: [San Francisco Maritime National Historical Park, hasShip, Alma]
Generated description
Alma is a historic wooden scow schooner preserved as a museum ship in San Francisco, representing the city’s 19th- and early 20th-century maritime commerce.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Alma
Target entity description: Alma is a historic wooden scow schooner preserved as a museum ship in San Francisco, representing the city’s 19th- and early 20th-century maritime commerce.
  • A. Zella
    Zella is an activewear and athleisure clothing brand known for its performance-focused yet stylish designs, sold at Nordstrom.
  • B. Alva
    Alva is the middle name of the famed American inventor Thomas Edison, often used as part of his full name, Thomas Alva Edison.
  • C. Loralai
    Loralai is a town and district in northern Balochistan, Pakistan, known historically as a regional administrative and trade center.
  • D. Rebeca
    Rebeca is a feminine given name, commonly used in Spanish- and Portuguese-speaking countries, that is a variant of the name Rebecca.
  • E. Priscilla
    Priscilla is a feminine given name of Latin origin, commonly used in English-speaking countries.
  • 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_69a2e80111fc8190961d5b7c6154123f completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f01be4108190b4c13346afd95a03 completed Feb. 28, 2026, 1:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69a42a1498808190a3639dedfe8ab5ea completed March 1, 2026, 11:59 a.m.
NEDg Description generation batch_69a42a69729881909d2a549e8601b66a completed March 1, 2026, noon
NED2 Entity disambiguation (via description) batch_69a42ac5d8f481908b59c72cf3698021 completed March 1, 2026, 12:02 p.m.
Created at: Feb. 28, 2026, 1:09 p.m.