Triple
T20950642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Crystal Egg |
E515965
|
entity |
| Predicate | imaginaryWorld |
P141829
|
FINISHED |
| Object | Mars as seen through the crystal |
—
|
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: Mars as seen through the crystal | Statement: [The Crystal Egg, imaginaryWorld, Mars as seen through the crystal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: imaginaryWorld Context triple: [The Crystal Egg, imaginaryWorld, Mars as seen through the crystal]
-
A.
worldType
Indicates the classification or category of world or environment that an entity is associated with.
-
B.
imaginaryEnemy
Indicates that one entity regards another as an enemy that exists only in imagination rather than in reality.
-
C.
realm
Indicates that one entity is a domain, sphere of influence, or area of control associated with another entity.
-
D.
worldName
Indicates that an entity has or is associated with a specific world’s name.
-
E.
oneOfWorlds
Indicates that an entity is a member of, or belongs to, a specified set or collection of possible worlds.
- 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fadd3bd88190a0d1fdea9d300fc0 |
completed | April 21, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69e5c9b1bae48190a845165fed1b005e |
completed | April 20, 2026, 6:37 a.m. |
| PDg | Predicate description generation | batch_69e5d53d22d08190bc17ed4bed53804a |
completed | April 20, 2026, 7:26 a.m. |
Created at: April 16, 2026, 1:26 p.m.