Triple
T34755068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château d’Eau du Peyrou |
E1001893
|
entity |
| Predicate | situatedOnElevation |
P149356
|
FINISHED |
| Object |
Peyrou hill
Peyrou hill is a prominent elevated site in Montpellier, France, known for its panoramic views over the city and its historic architectural ensemble, including the Château d’Eau and the Promenade du Peyrou.
|
E2111517
|
NE FINISHED |
How this triple was built (3 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: Peyrou hill | Statement: [Château d’Eau du Peyrou, situatedOnElevation, Peyrou hill]
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: Peyrou hill Triple: [Château d’Eau du Peyrou, situatedOnElevation, Peyrou hill]
Generated description
Peyrou hill is a prominent elevated site in Montpellier, France, known for its panoramic views over the city and its historic architectural ensemble, including the Château d’Eau and the Promenade du Peyrou.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: situatedOnElevation Context triple: [Château d’Eau du Peyrou, situatedOnElevation, Peyrou hill]
-
A.
locatedOnPeak
chosen
Indicates that one entity is situated at or on the summit or highest point of another entity (a peak).
-
B.
foundInElevation
Indicates that something exists, occurs, or is located at a particular elevation or height above a reference level.
-
C.
campElevation
Indicates the elevation or height above sea level at which a camp is located.
-
D.
elevationAboveSurroundingPlains
Indicates that something is situated at a higher altitude than the nearby flat or low-lying surrounding plains.
-
E.
elevationApproxMeters
Indicates the approximate elevation of an entity above sea level, measured in meters.
- F. None of above.
Provenance (6 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_69f76db0fb30819096709d43f9a1f45f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f77ffa6b68819090257fed3802c239 |
completed | May 3, 2026, 5:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37663037e481908f31588458b55800 |
completed | June 21, 2026, 4:18 a.m. |
| NEDg | Description generation | batch_6a3768cd30a48190a11841ed9010278c |
completed | June 21, 2026, 4:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a376943e3108190904c01d27e73c367 |
completed | June 21, 2026, 4:32 a.m. |
| PD | Predicate disambiguation | batch_69f7795978c481909e152cd1bd02dd07 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 3:59 p.m.