Triple

T6838680
Position Surface form Disambiguated ID Type / Status
Subject Ramparts of Avignon E157514 entity
Predicate hasGate P4365 FINISHED
Object Porte Thiers
Porte Thiers is a historic city gate integrated into the medieval ramparts of Avignon in southern France.
E630462 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: Porte Thiers | Statement: [Ramparts of Avignon, hasGate, Porte Thiers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porte Thiers
Context triple: [Ramparts of Avignon, hasGate, Porte Thiers]
  • A. Porte de la République
    Porte de la République is a historic city gate in Avignon, France, forming part of the town’s medieval fortifications.
  • B. Porte Guillaume
    Porte Guillaume is a historic triumphal arch in Dijon, France, serving as a prominent architectural symbol of the city.
  • C. Porte du Soubeyran
    Porte du Soubeyran is a historic medieval city gate and landmark in the town of Marvejols in southern France.
  • D. Porte Saint-Georges
    Porte Saint-Georges is a historic city gate in Vendôme, France, notable as a remnant of the town’s medieval fortifications.
  • E. Porte de Vincennes
    Porte de Vincennes is a major Parisian intersection and metro station in the 12th arrondissement, serving as a key gateway between central Paris and its eastern suburbs.
  • 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: Porte Thiers
Triple: [Ramparts of Avignon, hasGate, Porte Thiers]
Generated description
Porte Thiers is a historic city gate integrated into the medieval ramparts of Avignon in southern France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Porte Thiers
Target entity description: Porte Thiers is a historic city gate integrated into the medieval ramparts of Avignon in southern France.
  • A. Porte de la République
    Porte de la République is a historic city gate in Avignon, France, forming part of the town’s medieval fortifications.
  • B. Porte Guillaume
    Porte Guillaume is a historic triumphal arch in Dijon, France, serving as a prominent architectural symbol of the city.
  • C. Porte du Soubeyran
    Porte du Soubeyran is a historic medieval city gate and landmark in the town of Marvejols in southern France.
  • D. Porte Saint-Georges
    Porte Saint-Georges is a historic city gate in Vendôme, France, notable as a remnant of the town’s medieval fortifications.
  • E. Porte de Vincennes
    Porte de Vincennes is a major Parisian intersection and metro station in the 12th arrondissement, serving as a key gateway between central Paris and its eastern suburbs.
  • 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_69c6882c53608190b99aebef079b23bd completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d67ee1c88190b82a9b6b3d1e3875 completed March 27, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c75832278c8190b27ee9931f94a15e completed March 28, 2026, 4:25 a.m.
NEDg Description generation batch_69c759fa97348190bd0cec279878e9d6 completed March 28, 2026, 4:32 a.m.
NED2 Entity disambiguation (via description) batch_69c75a253b80819080f4566abf377186 completed March 28, 2026, 4:33 a.m.
Created at: March 27, 2026, 2:19 p.m.