Triple
T31513530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cimetière de la Rue-Petillon, Fleurbaix, France |
E804005
|
entity |
| Predicate | locatedNearFrontLineOf |
P61842
|
FINISHED |
| Object | Western Front in France |
E30816
|
NE 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: Western Front in France | Statement: [Cimetière de la Rue-Petillon, Fleurbaix, France, locatedNearFrontLineOf, Western Front in France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedNearFrontLineOf Context triple: [Cimetière de la Rue-Petillon, Fleurbaix, France, locatedNearFrontLineOf, Western Front in France]
-
A.
frontLineNear
chosen
Indicates that one entity is located close to the primary boundary or front line associated with another entity.
-
B.
frontLineBetween
Indicates that a boundary or line of direct confrontation exists separating two opposing sides or regions.
-
C.
locatedOnFront
Indicates that one entity is positioned on the front side or face of another entity.
-
D.
frontOf
Indicates that one entity is positioned directly before another along a primary viewing or movement direction.
-
E.
frontLineReached
Indicates that an entity has arrived at or crossed into the designated front line or primary boundary of engagement.
- F. None of above.
Provenance (4 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_69f348ceb0a48190ae7feca263b6296c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a019dfc69fc8190b0d80279a6216ba7 |
completed | May 11, 2026, 9:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b562a528c819089774c34089107a0 |
completed | June 12, 2026, 12:43 a.m. |
| PD | Predicate disambiguation | batch_6a019d54586c81908292d4880db9fad2 |
completed | May 11, 2026, 9:11 a.m. |
Created at: April 30, 2026, 9:51 p.m.