Triple
T23142244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | canton of Pont-l’Évêque |
E577493
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Le Faulq
Le Faulq is a small commune in the Calvados department of the Normandy region in northwestern France.
|
E1574129
|
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: Le Faulq | Statement: [canton of Pont-l’Évêque, contains, Le Faulq]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Le Faulq Context triple: [canton of Pont-l’Évêque, contains, Le Faulq]
-
A.
Lasauvage
Lasauvage is a small village in southwestern Luxembourg, known for its historical iron-mining heritage and proximity to the industrial town of Differdange.
-
B.
Fitzwilly
Fitzwilly is a 1967 comedy film starring Dick Van Dyke as a butler who masterminds elaborate thefts to support his employer’s fading fortune.
-
C.
Sauvestre
Sauvestre is a French surname most notably associated with architect Stephen Sauvestre, who contributed to the design of the Eiffel Tower.
-
D.
Lauzelle
Lauzelle is a district of the planned university town of Louvain-la-Neuve in Belgium, known for its residential areas and proximity to green spaces such as the Bois de Lauzelle.
-
E.
Scarphe
Scarphe is a figure from Greek mythology known primarily as the wife of Aeson, the father of the hero Jason.
- 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: Le Faulq Triple: [canton of Pont-l’Évêque, contains, Le Faulq]
Generated description
Le Faulq is a small commune in the Calvados department of the Normandy region in northwestern France.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Le Faulq Target entity description: Le Faulq is a small commune in the Calvados department of the Normandy region in northwestern France.
-
A.
Lasauvage
Lasauvage is a small village in southwestern Luxembourg, known for its historical iron-mining heritage and proximity to the industrial town of Differdange.
-
B.
Fitzwilly
Fitzwilly is a 1967 comedy film starring Dick Van Dyke as a butler who masterminds elaborate thefts to support his employer’s fading fortune.
-
C.
Sauvestre
Sauvestre is a French surname most notably associated with architect Stephen Sauvestre, who contributed to the design of the Eiffel Tower.
-
D.
Lauzelle
Lauzelle is a district of the planned university town of Louvain-la-Neuve in Belgium, known for its residential areas and proximity to green spaces such as the Bois de Lauzelle.
-
E.
Scarphe
Scarphe is a figure from Greek mythology known primarily as the wife of Aeson, the father of the hero Jason.
- 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_69e245f8e6248190ba3d58e068b4dccb |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ecb72fc8190a24e8f5756217a36 |
completed | April 29, 2026, 4:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c308fd60c8190afd340bd74423220 |
completed | May 19, 2026, 9:42 a.m. |
| NEDg | Description generation | batch_6a0c32dc646081909d3c36d089d61c00 |
completed | May 19, 2026, 9:52 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c35636e908190ae11d96deb15e1f5 |
completed | May 19, 2026, 10:03 a.m. |
Created at: April 17, 2026, 4 p.m.