Triple
T10063028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Historic Centre of San Gimignano |
E213032
|
entity |
| Predicate | numberOfSurvivingTowers |
P43196
|
FINISHED |
| Object | 14 |
—
|
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: 14 | Statement: [Historic Centre of San Gimignano, numberOfSurvivingTowers, 14]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfSurvivingTowers Context triple: [Historic Centre of San Gimignano, numberOfSurvivingTowers, 14]
-
A.
numberOfTowers
Indicates the quantity of towers associated with or contained by a given entity.
-
B.
numberOfDistrictsDestroyed
Indicates the quantity of districts that have been destroyed in a given context or event.
-
C.
towerCount
chosen
Indicates the number of towers associated with or present in a given entity or context.
-
D.
secondBuildingDestroyedBy
Indicates that the second building in a specified context is the one that was destroyed by a particular agent or event.
-
E.
buildingsDestroyed
Indicates that one or more buildings have been damaged to the point of destruction as a result of some event or action.
- 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_69ca83977128819084084eb7d1d8c52a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdcfd4e4ac8190a37061b4082caa48 |
completed | April 2, 2026, 2:09 a.m. |
| PD | Predicate disambiguation | batch_69cd4b92573481909389bc6148ae7ea8 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 8:58 p.m.