Triple

T2931781
Position Surface form Disambiguated ID Type / Status
Subject shelling of the Four Courts in Dublin E78970 entity
Predicate commanderSide2 P32311 FINISHED
Object Liam Mellows
Liam Mellows was an Irish republican leader and revolutionary who played a prominent role in both the Easter Rising of 1916 and the Irish Civil War.
E312019 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: Liam Mellows | Statement: [shelling of the Four Courts in Dublin, commanderSide2, Liam Mellows]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liam Mellows
Context triple: [shelling of the Four Courts in Dublin, commanderSide2, Liam Mellows]
  • A. Luke Monaghan
    Luke Monaghan is the brother of actor Dominic Monaghan, known for his work behind the camera as a director and filmmaker.
  • B. Liam Lonergan
    Liam Lonergan is an Irish businessman best known as one of the founders of the low-cost airline Ryanair.
  • C. Adam Hann-Byrd
    Adam Hann-Byrd is an American actor best known for his childhood role as a prodigy in the film "Little Man Tate."
  • D. Daniel Millar
    Daniel Millar is an actor known for his role in the National Theatre’s acclaimed stage production of "Frankenstein."
  • E. Liam Sullivan
    Liam Sullivan was an American character actor known for his numerous television and film roles from the 1950s through the 1980s, often portraying suave or villainous figures.
  • 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: Liam Mellows
Triple: [shelling of the Four Courts in Dublin, commanderSide2, Liam Mellows]
Generated description
Liam Mellows was an Irish republican leader and revolutionary who played a prominent role in both the Easter Rising of 1916 and the Irish Civil War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Liam Mellows
Target entity description: Liam Mellows was an Irish republican leader and revolutionary who played a prominent role in both the Easter Rising of 1916 and the Irish Civil War.
  • A. Luke Monaghan
    Luke Monaghan is the brother of actor Dominic Monaghan, known for his work behind the camera as a director and filmmaker.
  • B. Liam Lonergan
    Liam Lonergan is an Irish businessman best known as one of the founders of the low-cost airline Ryanair.
  • C. Adam Hann-Byrd
    Adam Hann-Byrd is an American actor best known for his childhood role as a prodigy in the film "Little Man Tate."
  • D. Daniel Millar
    Daniel Millar is an actor known for his role in the National Theatre’s acclaimed stage production of "Frankenstein."
  • E. Liam Sullivan
    Liam Sullivan was an American character actor known for his numerous television and film roles from the 1950s through the 1980s, often portraying suave or villainous figures.
  • 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_69ad8b0d40b481908bc2a5fa2e73c3fb completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9e0fec048190bdd70c60ec5c92cd completed March 8, 2026, 4:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69b086740d648190927afcb6bd25ccb1 completed March 10, 2026, 9 p.m.
NEDg Description generation batch_69b0df2b824c8190b7615af06f588644 completed March 11, 2026, 3:19 a.m.
NED2 Entity disambiguation (via description) batch_69b0dfed672c8190a5ce365ce31182be completed March 11, 2026, 3:22 a.m.
Created at: March 8, 2026, 2:55 p.m.