Triple
T28301747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isabella |
E713726
|
entity |
| Predicate | keepsRelicOfLover |
P18543
|
FINISHED |
| Object | Lorenzo’s severed head |
—
|
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: Lorenzo’s severed head | Statement: [Isabella, keepsRelicOfLover, Lorenzo’s severed head]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keepsRelicOfLover Context triple: [Isabella, keepsRelicOfLover, Lorenzo’s severed head]
-
A.
containsRelic
chosen
Indicates that one entity holds, includes, or has within it a relic.
-
B.
relicBroughtBy
Indicates that a relic was transported or delivered to a location or context by a specific agent or entity.
-
C.
notableRelic
Indicates that an entity is a historically or culturally significant relic associated with another entity (such as a place, person, or event).
-
D.
relicsAssociatedWith
Indicates a relationship where certain relics are connected or linked to a particular entity, context, or subject (such as a person, place, event, or tradition).
-
E.
protagonistLover
Indicates that one entity is the romantic partner or love interest of the story’s protagonist.
- 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_69efb524ab688190a1ce7ee7c9520932 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f644b2eba4819093973b8eeb3ed63d |
completed | May 2, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 11:35 p.m.