Triple
T33416638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Porte d’Italie |
E855735
|
entity |
| Predicate | onFormerCityWall |
P104371
|
FINISHED |
| Object | Thiers wall of 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: Thiers wall of Paris | Statement: [Porte d’Italie, onFormerCityWall, Thiers wall of Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onFormerCityWall Context triple: [Porte d’Italie, onFormerCityWall, Thiers wall of Paris]
-
A.
followsOldCityWall
chosen
Indicates that something runs along or traces the path of an old city wall.
-
B.
hasCityWallName
Indicates that a city wall is associated with a specific name or designation.
-
C.
hasCityWallsFrom
Indicates that a city’s defensive walls originate from, or were constructed starting at, a specified source location or structure.
-
D.
hadCityWalls
Indicates that a city or settlement possessed defensive walls surrounding it.
-
E.
hasCityWallOrientation
Indicates the directional orientation or alignment of a city’s defensive wall relative to cardinal or geographic directions.
- 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_69f3496fdf0081908c1aa30870ce518b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e47f37848190aadb137c81760f1f |
completed | May 3, 2026, 6 a.m. |
| PD | Predicate disambiguation | batch_69f6e3da41948190a4cfe866ce184f73 |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:36 a.m.