Triple
T31122757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ordinances of Saint-Cloud |
E793265
|
entity |
| Predicate | mainLocationOfImpact |
P87330
|
FINISHED |
| Object | Paris |
—
|
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: Paris | Statement: [Ordinances of Saint-Cloud, mainLocationOfImpact, Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainLocationOfImpact Context triple: [Ordinances of Saint-Cloud, mainLocationOfImpact, Paris]
-
A.
actualImpactSite
Indicates the location where an impact actually occurred, as opposed to a predicted, intended, or nominal impact site.
-
B.
sectorMostAffected
Indicates that a particular sector is the one experiencing the greatest impact or disruption relative to others in a given context.
-
C.
hazardConcentratedAt
Indicates that a hazardous substance or condition is present with elevated intensity or density at a specific location or point.
-
D.
mainLocation
Indicates that one entity serves as the primary or central location associated with another entity.
-
E.
notableLocationOfDamage
chosen
Indicates the specific place where damage is prominently present or has significantly occurred.
- 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_69f224d0a7688190af3fe3e6e26d01ed |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: April 29, 2026, 9:05 p.m.