Triple
T3767438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Monument historique (France) |
E82712
|
entity |
| Predicate | higherProtectionLevel |
P29844
|
FINISHED |
| Object | classé monument historique |
—
|
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: classé monument historique | Statement: [Monument historique (France), higherProtectionLevel, classé monument historique]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: higherProtectionLevel Context triple: [Monument historique (France), higherProtectionLevel, classé monument historique]
-
A.
protectionLevel
Indicates the degree or extent to which something is safeguarded against harm, risk, or unauthorized access.
-
B.
expandedProtectionTo
Indicates that an existing protection, safeguard, or coverage was broadened to include an additional entity, group, area, or scope.
-
C.
addsProtectionFor
Indicates that one entity provides or increases protective measures or safeguards for another entity.
-
D.
isStrongerProtectionThan
chosen
Indicates that one form of protection provides a higher level of security, defense, or safeguarding compared to another.
-
E.
higherTierAuthority
Indicates that one entity holds a superior or higher-ranking level of authority or control over another entity.
- 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_69ad8b207b0081909d2b48843fbd8795 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc2bdf6c819088d3c6ace83ca5ea |
completed | March 8, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69adc04ec36c8190bd5b944d4f4d32aa |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:35 p.m.