Triple
T37715438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archangel |
E939442
|
entity |
| Predicate | formerPowers |
P99992
|
FINISHED |
| Object | natural feathered wings |
—
|
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: natural feathered wings | Statement: [Archangel, formerPowers, natural feathered wings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerPowers Context triple: [Archangel, formerPowers, natural feathered wings]
-
A.
formerOverlordPower
Indicates that one entity previously held overlord or colonial authority over another entity, but no longer does so.
-
B.
wasPowerfulIn
Indicates that an entity possessed significant power, influence, or effectiveness within a specified domain, context, or time period.
-
C.
notableAbsorbedPowersFrom
Indicates that one entity is known for having taken in or acquired powers or abilities from another entity.
-
D.
heroPower
chosen
Indicates that an entity possesses or is associated with a particular heroic power or special ability.
-
E.
previousPowerType
Indicates that one entity’s power type immediately preceded another entity’s power type in a sequence or history.
- 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_69f76edc208c8190bc8b9683f75e1024 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a011ee3507081908b42de4278ae0b83 |
completed | May 11, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_6a011e874420819091cac3f08e8aa3f9 |
completed | May 11, 2026, 12:10 a.m. |
Created at: May 3, 2026, 4:18 p.m.