Triple
T38575709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Secteur fortifié de Savoie |
E929395
|
entity |
| Predicate | borderToBeDefended |
P201988
|
FINISHED |
| Object | Italy |
—
|
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: Italy | Statement: [Secteur fortifié de Savoie, borderToBeDefended, Italy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderToBeDefended Context triple: [Secteur fortifié de Savoie, borderToBeDefended, Italy]
-
A.
borderDefenseType
Indicates the specific kind or category of defensive measure or system employed along a border.
-
B.
riverDefended
Indicates that a river is actively protected or guarded against threats, such as environmental damage, encroachment, or hostile actions.
-
C.
fortressDefended
Indicates that a fortress is actively protected against threats or attacks by some defending force.
-
D.
builtToDefendAgainst
Indicates that something was constructed or designed specifically for the purpose of protecting against or countering a particular threat, entity, or type of attack.
-
E.
defendedTown
Indicates that an entity protected or guarded a town from harm, attack, or threat.
- F. None of above. chosen
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_69f76ebd2248819083978362d81fa35e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a003ffb548081908ba64fd2b570f42f |
completed | May 10, 2026, 8:21 a.m. |
| PD | Predicate disambiguation | batch_6a003fcecf788190a13dff38b9de3414 |
completed | May 10, 2026, 8:20 a.m. |
| PDg | Predicate description generation | batch_6a003ffa64e48190b37cce7d1c939b78 |
completed | May 10, 2026, 8:21 a.m. |
Created at: May 3, 2026, 4:32 p.m.