Triple
T30596454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hong Kong Sanctum |
E778800
|
entity |
| Predicate | universeDivision |
P129869
|
FINISHED |
| Object | Earth-199999 |
—
|
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: Earth-199999 | Statement: [Hong Kong Sanctum, universeDivision, Earth-199999]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: universeDivision Context triple: [Hong Kong Sanctum, universeDivision, Earth-199999]
-
A.
cosmicDivisionOf
chosen
Indicates a relationship in which a larger cosmic whole is partitioned into distinct regions, realms, or components.
-
B.
universe
Indicates that something pertains to, exists within, or is associated with the entirety of space, time, matter, and phenomena collectively referred to as the universe.
-
C.
inUniverse
Indicates that one entity exists, occurs, or is set within the fictional or conceptual universe defined by another entity.
-
D.
cosmologicalRealm
Indicates that one entity exists in, belongs to, or is associated with a particular cosmological realm or plane of existence relative to another.
-
E.
typicalUniverse
Indicates that something represents or belongs to a standard, representative, or commonly occurring universe within a given context or model.
- 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_69f224a1570c8190a85d3ac330479a79 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f697eabb048190bc01a830f14942c6 |
completed | May 3, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_69f69664142c8190bc695501056b0236 |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 29, 2026, 8:24 p.m.