Triple
T28824409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William II of Villehardouin |
E727862
|
entity |
| Predicate | fortificationBuilt |
P165636
|
FINISHED |
| Object | Castle of Mistra |
—
|
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: Castle of Mistra | Statement: [William II of Villehardouin, fortificationBuilt, Castle of Mistra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fortificationBuilt Context triple: [William II of Villehardouin, fortificationBuilt, Castle of Mistra]
-
A.
fortifiedBuilding
Indicates that a building is strengthened or reinforced for defense against attacks or intrusions.
-
B.
fortressBuiltAs
Indicates that a fortress was originally constructed to serve as a particular type, role, or function.
-
C.
fortificationTypeDefended
Indicates the specific type of fortification that an entity is responsible for defending or protecting.
-
D.
wasFortifiedBy
Indicates that a place or structure received defensive strengthening or fortification through the actions or resources of a specified agent or entity.
-
E.
fortificationCommanded
Indicates that one entity holds authority over and directs the defense or operation of a particular fortification or fortified structure.
- 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_69f0319d09088190bbf14cdf1987792a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6596b210481908af6cd555748f75b |
completed | May 2, 2026, 8:07 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f658ebeca4819096beb3f98f73fe31 |
completed | May 2, 2026, 8:05 p.m. |
Created at: April 28, 2026, 6:35 a.m.