Triple
T8499092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Towns of Djenné |
E201169
|
entity |
| Predicate | inscriptionStatus |
P83062
|
FINISHED |
| Object | List of World Heritage in Danger |
—
|
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: List of World Heritage in Danger | Statement: [Old Towns of Djenné, inscriptionStatus, List of World Heritage in Danger]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionStatus Context triple: [Old Towns of Djenné, inscriptionStatus, List of World Heritage in Danger]
-
A.
registrationStatus
Indicates the current state or condition of an entity’s enrollment or registration within a given system or process.
-
B.
inscriptionBy
Indicates that an inscription was created, written, or carved by a particular agent or entity.
-
C.
inscription
Indicates that text has been written, carved, or engraved onto a surface or object.
-
D.
inscriptionCompleteness
Indicates how fully or partially an inscription is preserved or recorded in relation to its original state.
-
E.
inscriptionBody
Indicates that the predicate links an inscription to the textual content or wording that is inscribed.
- 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_69ca831ee390819095fae73400bbfafc |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5984d7481908c41c57bef9cf254 |
completed | March 31, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69cbd10a4b0881909e254117780dc823 |
completed | March 31, 2026, 1:50 p.m. |
| PDg | Predicate description generation | batch_69cbe30d453481908f897ed2b06e7534 |
completed | March 31, 2026, 3:06 p.m. |
Created at: March 30, 2026, 6:14 p.m.