Triple
T36273665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2023 Marrakesh–Safi earthquake |
E892742
|
entity |
| Predicate | historicSiteDamaged |
P130459
|
FINISHED |
| Object | Koutoubia Mosque surroundings |
—
|
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: Koutoubia Mosque surroundings | Statement: [2023 Marrakesh–Safi earthquake, historicSiteDamaged, Koutoubia Mosque surroundings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicSiteDamaged Context triple: [2023 Marrakesh–Safi earthquake, historicSiteDamaged, Koutoubia Mosque surroundings]
-
A.
hasRuinsOn
Indicates that one location or object contains or is the site of ruins situated upon it.
-
B.
infrastructureRemnants
Indicates that physical traces or leftover elements of infrastructure remain present from a previous construction, system, or facility.
-
C.
landmarksDestroyed
chosen
Indicates that certain notable or significant physical landmarks have been damaged or completely destroyed.
-
D.
historicLocation
Indicates that an entity is situated in or associated with a place of historical significance.
-
E.
hasHistoricSite
Indicates that an entity possesses, contains, or is associated with a place recognized for its historical significance.
- 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_69f76e488f34819083e254dbe288c27a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a01203ac018819085d7c9abd8345b23 |
completed | May 11, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_6a011f3f149c819090749722da0e3413 |
completed | May 11, 2026, 12:13 a.m. |
Created at: May 3, 2026, 4:09 p.m.