Triple
T30596356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Sanctum |
E778798
|
entity |
| Predicate | sisterSanctum |
P169597
|
FINISHED |
| Object | London Sanctum |
—
|
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: London Sanctum | Statement: [New York Sanctum, sisterSanctum, London Sanctum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sisterSanctum Context triple: [New York Sanctum, sisterSanctum, London Sanctum]
-
A.
sisterFate
Indicates a relationship where one entity is destined to share or mirror the fate or outcome of another, as if bound together like sisters in destiny.
-
B.
sisterShow
Indicates that two shows are related as sister shows, typically sharing common origins, networks, or production ties without one being derived from the other.
-
C.
hasSisterProtagonists
Indicates that the work features two or more main characters who are sisters as its central protagonists.
-
D.
sisterCharacter
Indicates that one character is the sister of another character.
-
E.
sisterTeam
Indicates that two teams are closely affiliated or paired, typically within the same organization or structure, as "sister" teams.
- 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_69f224a1570c8190a85d3ac330479a79 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6897fc2e881909e2bd183eb7fddc9 |
completed | May 2, 2026, 11:32 p.m. |
| PD | Predicate disambiguation | batch_69f67e448a9c8190b591374d98799fe3 |
completed | May 2, 2026, 10:44 p.m. |
| PDg | Predicate description generation | batch_69f67f0353c88190a05b2db449abe0f4 |
completed | May 2, 2026, 10:47 p.m. |
Created at: April 29, 2026, 8:24 p.m.