Triple
T34624096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abbey of Saint-Germain-des-Prés |
E889084
|
entity |
| Predicate | cityQuarterGaveNameTo |
P24038
|
FINISHED |
| Object | Saint-Germain-des-Prés neighborhood |
—
|
NE NERFINISHED |
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: Saint-Germain-des-Prés neighborhood | Statement: [Abbey of Saint-Germain-des-Prés, cityQuarterGaveNameTo, Saint-Germain-des-Prés neighborhood]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cityQuarterGaveNameTo Context triple: [Abbey of Saint-Germain-des-Prés, cityQuarterGaveNameTo, Saint-Germain-des-Prés neighborhood]
-
A.
cityQuarterNumber
Indicates the specific numbered quarter or district within a city to which an entity belongs or is associated.
-
B.
cityNamedAfter
Indicates that one city derives its name from or was named in honor of another entity, such as a person, place, or concept.
-
C.
cityQuarterCharacter
Indicates the characteristic qualities or distinctive nature that define a particular city quarter.
-
D.
districtNameOrigin
chosen
Indicates that the relationship specifies the origin or source from which a district’s name is derived.
-
E.
situatedInQuarter
Indicates that one entity is located within or belongs to a specific quarter or district of a larger area.
- 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_69f349d64a388190a013cfa9bd33fad7 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7234bcaa48190ac970759d34e254a |
completed | May 3, 2026, 10:28 a.m. |
| PD | Predicate disambiguation | batch_69f72155c48881909bd40b9aa3febd5a |
completed | May 3, 2026, 10:20 a.m. |
Created at: May 1, 2026, 2:04 a.m.