Triple
T28059305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | defence of the Escaut (1940) |
E709056
|
entity |
| Predicate | riverDefended |
P169272
|
FINISHED |
| Object | Escaut |
—
|
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: Escaut | Statement: [defence of the Escaut (1940), riverDefended, Escaut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverDefended Context triple: [defence of the Escaut (1940), riverDefended, Escaut]
-
A.
fortressDefended
Indicates that a fortress is actively protected against threats or attacks by some defending force.
-
B.
townDefendedBy
Indicates that a particular town is protected or guarded by a specified defending force or entity.
-
C.
houseDefendedFrom
Indicates that one entity (typically a house) is protected or shielded against threats, attacks, or harm originating from another specified entity or source.
-
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.
coastalDefense
Indicates a defensive relationship in which structures, systems, or actions are used to protect a coastline or shore area from threats such as erosion, flooding, or attack.
- 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_69ef9b6eb6d88190a3fea236eb0f7bed |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f67d691a948190afa7fb19ae7d4ac5 |
completed | May 2, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f678cc272081909e5c70f1bc7407f0 |
completed | May 2, 2026, 10:21 p.m. |
| PDg | Predicate description generation | batch_69f67c9ec1708190b26ccf402ed7b106 |
completed | May 2, 2026, 10:37 p.m. |
Created at: April 27, 2026, 8:38 p.m.