Triple
T33737425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viserion |
E864457
|
entity |
| Predicate | eyeColorAfterResurrection |
P21689
|
FINISHED |
| Object |
blue (television series)
Blue is an American drama web television series that follows a single mother who secretly works as an escort while trying to raise her teenage son.
|
E2065278
|
NE FINISHED |
How this triple was built (3 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: blue (television series) | Statement: [Viserion, eyeColorAfterResurrection, blue (television series)]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: blue (television series) Triple: [Viserion, eyeColorAfterResurrection, blue (television series)]
Generated description
Blue is an American drama web television series that follows a single mother who secretly works as an escort while trying to raise her teenage son.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eyeColorAfterResurrection Context triple: [Viserion, eyeColorAfterResurrection, blue (television series)]
-
A.
earColor
Indicates the relationship between an entity and the color characteristic of its ear or ears.
-
B.
eyePatchColor
Indicates the color attribute associated with an eye patch worn by an entity.
-
C.
hasEyeColor
chosen
Indicates that an entity possesses eyes of a specified color.
-
D.
eyeType
Indicates the specific kind or category of eyes an entity has, such as their form, structure, or visual style.
-
E.
eyeCharacteristic
Indicates a relationship where an entity possesses a specific attribute, feature, or quality of its eyes.
- F. None of above.
Provenance (6 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_69f3498b24b8819096a65009e521d0e1 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fb54446881909265a17685fa5e4a |
completed | May 3, 2026, 7:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a365c83744081909481fa252ac06e3f |
completed | June 20, 2026, 9:25 a.m. |
| NEDg | Description generation | batch_6a365da4c1ac81908efaf06a0693eb33 |
completed | June 20, 2026, 9:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a365e7256e881908c84b71fd26f8b22 |
completed | June 20, 2026, 9:33 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:44 a.m.