Triple
T30713988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Natalia Alianovna Romanova |
E781970
|
entity |
| Predicate | mcuFirstAppearanceYear |
P3297
|
FINISHED |
| Object | 2010 |
—
|
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: 2010 | Statement: [Natalia Alianovna Romanova, mcuFirstAppearanceYear, 2010]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mcuFirstAppearanceYear Context triple: [Natalia Alianovna Romanova, mcuFirstAppearanceYear, 2010]
-
A.
mcuDebut
Indicates the work, appearance, or context in which a character or entity first appears within the Marvel Cinematic Universe.
-
B.
firstPrototypeYear
Indicates the year in which the first prototype of an entity was created or completed.
-
C.
productionModelDebut
Indicates the event or point in time when a model first enters official production or is publicly released as a production version.
-
D.
firstShowYear
Indicates the year in which something (such as a show, event, or work) was first presented or made publicly available.
-
E.
introducedInYear
chosen
Indicates the year in which something was first introduced, launched, or made available.
- 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_69f224acd24481908ed5f96f0d69b5dd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6953bafb88190a860e9c68a3dd4b2 |
completed | May 3, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69f690ed5d008190831cf8e44cce28af |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 29, 2026, 8:35 p.m.