Triple

T16238698
Position Surface form Disambiguated ID Type / Status
Subject Zong massacre E394182 entity
Predicate ship P880 FINISHED
Object Zong
Zong was a British slave ship infamous for the 1781 massacre in which its crew threw over a hundred enslaved Africans overboard to claim insurance, a pivotal atrocity in the history of the transatlantic slave trade.
 E1202845 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: Zong | Statement: [Zong massacre, ship, Zong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zong
Context triple: [Zong massacre, ship, Zong]
  • A. Port Liner
    Port Liner is an automated guideway transit system in Kobe, Japan, known as one of the world’s first driverless urban transit lines, linking central Kobe with Port Island.
  • B. Winnellie
    Winnellie is a suburb within the Darwin metropolitan area in Australia's Northern Territory, known for its industrial and commercial precincts.
  • C. Evergreen Marine
    Evergreen Marine is a major Taiwanese container shipping company known for operating one of the world’s largest fleets of container vessels.
  • D. Gracy
    Gracy is a given name, typically used as a feminine variant of the name Gracie or Grace.
  • E. Guncati
    Guncati is a village located within the municipality of Barajevo in the city of Belgrade, Serbia.
  • 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: Zong
Triple: [Zong massacre, ship, Zong]
Generated description
Zong was a British slave ship infamous for the 1781 massacre in which its crew threw over a hundred enslaved Africans overboard to claim insurance, a pivotal atrocity in the history of the transatlantic slave trade.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zong
Target entity description: Zong was a British slave ship infamous for the 1781 massacre in which its crew threw over a hundred enslaved Africans overboard to claim insurance, a pivotal atrocity in the history of the transatlantic slave trade.
  • A. Port Liner
    Port Liner is an automated guideway transit system in Kobe, Japan, known as one of the world’s first driverless urban transit lines, linking central Kobe with Port Island.
  • B. Winnellie
    Winnellie is a suburb within the Darwin metropolitan area in Australia's Northern Territory, known for its industrial and commercial precincts.
  • C. Evergreen Marine
    Evergreen Marine is a major Taiwanese container shipping company known for operating one of the world’s largest fleets of container vessels.
  • D. Gracy
    Gracy is a given name, typically used as a feminine variant of the name Gracie or Grace.
  • E. Guncati
    Guncati is a village located within the municipality of Barajevo in the city of Belgrade, Serbia.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2455c7a3c81909e3b42edf03be43e completed April 17, 2026, 2:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000edaf76c8190acc01f58845e570a completed May 10, 2026, 4:51 a.m.
NEDg Description generation batch_6a0011f7f3fc8190a3a3bf260b391e78 completed May 10, 2026, 5:04 a.m.
NED2 Entity disambiguation (via description) batch_6a0012e9913481908ee5ada2fce507f4 completed May 10, 2026, 5:08 a.m.
Created at: April 10, 2026, 5:04 a.m.