Triple

T6838678
Position Surface form Disambiguated ID Type / Status
Subject Ramparts of Avignon E157514 entity
Predicate hasGate P4365 FINISHED
Object Porte de l’Oulle
Porte de l’Oulle is a historic city gate in Avignon, France, forming part of the medieval fortifications that once protected the city.
 E627378 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 de l’Oulle | Statement: [Ramparts of Avignon, hasGate, Porte de l’Oulle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Porte de l’Oulle
Context triple: [Ramparts of Avignon, hasGate, Porte de l’Oulle]
  • A. Porte du Soubeyran
    Porte du Soubeyran is a historic medieval city gate and landmark in the town of Marvejols in southern France.
  • B. Porte de la Gardette
    Porte de la Gardette is a historic city gate in the medieval fortified town of Aigues-Mortes in southern France.
  • C. Porte de la Chapelle
    Porte de la Chapelle is a neighborhood and former city gate area in northern Paris known as a major transport hub and gateway into the city.
  • D. Porte Molitor
    Porte Molitor is a Paris Métro station in the 16th arrondissement of Paris, France.
  • E. Porte de Montreuil
    Porte de Montreuil is a Paris Métro station in the 20th arrondissement, serving a busy eastern gateway of the city near the Boulevard Périphérique.
  • 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 de l’Oulle
Triple: [Ramparts of Avignon, hasGate, Porte de l’Oulle]
Generated description
Porte de l’Oulle is a historic city gate in Avignon, France, forming part of the medieval fortifications that once protected the city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Porte de l’Oulle
Target entity description: Porte de l’Oulle is a historic city gate in Avignon, France, forming part of the medieval fortifications that once protected the city.
  • A. Porte du Soubeyran
    Porte du Soubeyran is a historic medieval city gate and landmark in the town of Marvejols in southern France.
  • B. Porte de la Gardette
    Porte de la Gardette is a historic city gate in the medieval fortified town of Aigues-Mortes in southern France.
  • C. Porte de la Chapelle
    Porte de la Chapelle is a neighborhood and former city gate area in northern Paris known as a major transport hub and gateway into the city.
  • D. Porte Molitor
    Porte Molitor is a Paris Métro station in the 16th arrondissement of Paris, France.
  • E. Porte de Montreuil
    Porte de Montreuil is a Paris Métro station in the 20th arrondissement, serving a busy eastern gateway of the city near the Boulevard Périphérique.
  • 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_69c748b5a7c08190983bd355a1bc76d7 completed March 28, 2026, 3:19 a.m.
NEDg Description generation batch_69c74a8717148190936dd9331b90e0db completed March 28, 2026, 3:27 a.m.
NED2 Entity disambiguation (via description) batch_69c74b08e6b48190ab0a4313ede456a8 completed March 28, 2026, 3:29 a.m.
Created at: March 27, 2026, 2:19 p.m.