Triple

T28117774
Position Surface form Disambiguated ID Type / Status
Subject Brown, Brothers & Co. (New York) ship Eliza Frances crew E710685 entity
Predicate operatedOnVessel P13018 FINISHED
Object ship Eliza Frances
The ship Eliza Frances was a 19th-century sailing vessel associated with the New York maritime firm Brown, Brothers & Co., known through records of its crew and voyages.
 E1801861 NE FINISHED

How this triple was built (3 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: ship Eliza Frances | Statement: [Brown, Brothers & Co. (New York) ship Eliza Frances crew, operatedOnVessel, ship Eliza Frances]
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: ship Eliza Frances
Triple: [Brown, Brothers & Co. (New York) ship Eliza Frances crew, operatedOnVessel, ship Eliza Frances]
Generated description
The ship Eliza Frances was a 19th-century sailing vessel associated with the New York maritime firm Brown, Brothers & Co., known through records of its crew and voyages.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: operatedOnVessel
Context triple: [Brown, Brothers & Co. (New York) ship Eliza Frances crew, operatedOnVessel, ship Eliza Frances]
  • A. operatesVessel chosen
    Indicates that an agent is responsible for controlling, managing, or running the operation of a vessel.
  • B. usesVesselsOperatedBy
    Indicates that one entity makes use of vessels that are operated or controlled by another entity.
  • C. hasVessel
    Indicates that one entity possesses, uses, or is associated with a particular vessel (such as a container, ship, or transport medium) in the context of the described relationship or action.
  • D. vesselTypeServedOn
    Indicates the type of vessel on which an entity has served or performed duty.
  • E. isVesselFor
    Indicates that one entity functions as a container or medium specifically used to hold, carry, or convey another entity.
  • F. None of above.

Provenance (6 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_69ef9b72f63081909dfbc2c1ddae86c6 completed April 27, 2026, 5:22 p.m.
NER Named-entity recognition batch_69fe744faca881908e11e90e0a35653f completed May 8, 2026, 11:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a15c9310d9c81909e0c28fccc08061e completed May 26, 2026, 4:24 p.m.
NEDg Description generation batch_6a15cac6172c8190b677d538dee18fb0 completed May 26, 2026, 4:31 p.m.
NED2 Entity disambiguation (via description) batch_6a15cb48691081909c5dde3e9a0db8f4 completed May 26, 2026, 4:33 p.m.
PD Predicate disambiguation batch_69fe734cbf7081909a552c5cf3b5ea59 completed May 8, 2026, 11:35 p.m.
Created at: April 27, 2026, 9:15 p.m.