Triple

T8978042
Position Surface form Disambiguated ID Type / Status
Subject Fréjus E214446 entity
Predicate hasLandmark P105 FINISHED
Object Porte d’Orée
Porte d’Orée is a historic Roman-era gate in Fréjus, France, notable as a remnant of the ancient city’s fortifications.
 E769788 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 d’Orée | Statement: [Fréjus, hasLandmark, Porte d’Orée]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Porte d’Orée
Context triple: [Fréjus, hasLandmark, Porte d’Orée]
  • A. Porte du Thérond
    Porte du Thérond is a historic fortified city gate in the medieval town of Marvejols in southern France.
  • B. Lalumière
    Lalumière is a French surname most notably borne by Catherine Lalumière, a prominent French politician and former European Parliament member.
  • C. La Garde-Freinet
    La Garde-Freinet is a picturesque Provençal village in southeastern France, known for its historic hilltop setting, chestnut forests, and views over the Gulf of Saint-Tropez.
  • D. La Neuve-Lyre
    La Neuve-Lyre is a small commune in northern France, located in the Eure department of the Normandy region.
  • E. La Passe
    La Passe is the principal village and harbor area on La Digue Island in the Seychelles, serving as its main hub for transport, tourism, and local commerce.
  • 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 d’Orée
Triple: [Fréjus, hasLandmark, Porte d’Orée]
Generated description
Porte d’Orée is a historic Roman-era gate in Fréjus, France, notable as a remnant of the ancient city’s fortifications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Porte d’Orée
Target entity description: Porte d’Orée is a historic Roman-era gate in Fréjus, France, notable as a remnant of the ancient city’s fortifications.
  • A. Porte du Thérond
    Porte du Thérond is a historic fortified city gate in the medieval town of Marvejols in southern France.
  • B. Lalumière
    Lalumière is a French surname most notably borne by Catherine Lalumière, a prominent French politician and former European Parliament member.
  • C. La Garde-Freinet
    La Garde-Freinet is a picturesque Provençal village in southeastern France, known for its historic hilltop setting, chestnut forests, and views over the Gulf of Saint-Tropez.
  • D. La Neuve-Lyre
    La Neuve-Lyre is a small commune in northern France, located in the Eure department of the Normandy region.
  • E. La Passe
    La Passe is the principal village and harbor area on La Digue Island in the Seychelles, serving as its main hub for transport, tourism, and local commerce.
  • 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_69ca839ea8b88190922c6a326ffcc0d3 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc67a33c8481909125acf4b7f0a919 completed April 1, 2026, 12:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc96e7eb48190a3df410b1544b997 completed April 3, 2026, 2:06 p.m.
NEDg Description generation batch_69cfca6202a4819090404b7893a31ba7 completed April 3, 2026, 2:10 p.m.
NED2 Entity disambiguation (via description) batch_69cfcaeaf24c81908daadfe954413778 completed April 3, 2026, 2:12 p.m.
Created at: March 30, 2026, 7:02 p.m.