Triple
T37146785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vauban fortifications of Villefranche-de-Conflent |
E920260
|
entity |
| Predicate | numberOfComponentsInSerialProperty |
P19198
|
FINISHED |
| Object | 12 |
—
|
LITERAL FINISHED |
How this triple was built (2 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: 12 | Statement: [Vauban fortifications of Villefranche-de-Conflent, numberOfComponentsInSerialProperty, 12]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfComponentsInSerialProperty Context triple: [Vauban fortifications of Villefranche-de-Conflent, numberOfComponentsInSerialProperty, 12]
-
A.
partOfSerialProperty
Indicates that a property belongs to, or is a component within, a larger serial or sequential collection of properties.
-
B.
hasComponentCount
chosen
Indicates that an entity is associated with a specific number of components it contains or comprises.
-
C.
typicalNumberOfComponents
Indicates the usual or standard count of distinct components that an entity is expected to have.
-
D.
numberOfSeries
Indicates the total count of distinct series associated with or contained within a given entity.
-
E.
isSerial
Indicates that an entity participates in or is characterized by a sequence of related events or items occurring one after another in order.
- F. None of above.
Provenance (3 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_69f76e9f87c08190b4c8f7fafbd8345a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:15 p.m.