Triple
T21062964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Free Zone (zone libre) |
E518896
|
entity |
| Predicate | demarcationLineWith |
P21958
|
FINISHED |
| Object | Occupied Zone (zone occupée) |
—
|
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: Occupied Zone (zone occupée) | Statement: [Free Zone (zone libre), demarcationLineWith, Occupied Zone (zone occupée)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: demarcationLineWith Context triple: [Free Zone (zone libre), demarcationLineWith, Occupied Zone (zone occupée)]
-
A.
divisionLine
chosen
Indicates a boundary or separating line that divides one area, group, or portion from another.
-
B.
demarcationType
Indicates the specific way in which a boundary or separation between entities is defined, marked, or categorized.
-
C.
definedLine
Indicates that a specific line (such as a boundary, path, or reference line) has been formally established or specified within a given context.
-
D.
rulingLine
Indicates that one entity is the ruling or governing lineage, dynasty, or family over another entity (such as a territory, people, or polity).
-
E.
damLine
Indicates that one entity is the maternal lineage or female ancestral line from which the other entity descends.
- 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_69e0b505ef108190b25dd4033e2ff7eb |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6feb15698819090246698b143cb56 |
completed | April 21, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf9d71881908cd85dfc37db93ca |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:39 p.m.