Triple
T35470598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Star Sapphire |
E1025195
|
entity |
| Predicate | sometimesAlignment |
P126902
|
FINISHED |
| Object | antihero |
—
|
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: antihero | Statement: [Star Sapphire, sometimesAlignment, antihero]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sometimesAlignment Context triple: [Star Sapphire, sometimesAlignment, antihero]
-
A.
sometimesAlignedAs
chosen
Indicates that two entities are occasionally in agreement, coordination, or matching orientation, but not consistently or permanently.
-
B.
generalAlignment
Indicates how closely two entities agree or are compatible in their overall position, stance, or orientation.
-
C.
typicalAlignment
Indicates the usual or most common way in which two entities are positioned, oriented, or arranged relative to each other.
-
D.
eraAlignment
Indicates that two entities are associated with, or correspond to, the same historical or temporal era.
-
E.
notAlignedWith
Indicates that one entity’s position, orientation, or viewpoint does not correspond or agree with that of another entity.
- 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_69f76dfa20d0819089585dc2cf653aea |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:04 p.m.