Triple
T35799581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edric Storm |
E1034930
|
entity |
| Predicate | appearanceResembles |
P35666
|
FINISHED |
| Object | Robert Baratheon in youth |
—
|
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: Robert Baratheon in youth | Statement: [Edric Storm, appearanceResembles, Robert Baratheon in youth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appearanceResembles Context triple: [Edric Storm, appearanceResembles, Robert Baratheon in youth]
-
A.
resembles
chosen
Indicates that one entity is similar in appearance, form, or characteristics to another.
-
B.
faceResemblance
Indicates that one entity’s facial appearance is similar to or resembles that of another entity.
-
C.
appearanceIncludes
Indicates that one entity’s visual or outward characteristics contain, feature, or incorporate those of another entity.
-
D.
appearance
Indicates how something looks or seems to an observer, including its visible form, condition, or outward impression.
-
E.
appearTo
Indicates that something gives the impression or seems to be a certain way to an observer, without confirming that it actually is so.
- 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_69f76e169bd081909f16cd8c9ee7870c |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fe6e492bf8819080b25221d13445ea |
completed | May 8, 2026, 11:14 p.m. |
| PD | Predicate disambiguation | batch_69fe6dd33a6881908fe9bbbc184cab51 |
completed | May 8, 2026, 11:12 p.m. |
Created at: May 3, 2026, 4:06 p.m.