Triple
T36377604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brandon Stark |
E895945
|
entity |
| Predicate | relationToLyannaStark |
P204849
|
FINISHED |
| Object | elder brother |
—
|
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: elder brother | Statement: [Brandon Stark, relationToLyannaStark, elder brother]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationToLyannaStark Context triple: [Brandon Stark, relationToLyannaStark, elder brother]
-
A.
predecessorAsLordOfWinterfell
Indicates that one entity previously held the title of Lord of Winterfell immediately before another entity.
-
B.
predecessorAtCasterlyRock
Indicates that one entity previously held a position or role at Casterly Rock before another entity.
-
C.
predecessorOnDragonstone
Indicates that one entity previously held a position, role, or status on Dragonstone before another entity.
-
D.
statusAfterTargaryens
Indicates the status or condition of something or someone following the period or rule of the Targaryens.
-
E.
relationshipToPrinceHal
Indicates the specific familial, social, or interpersonal connection that an entity has to Prince Hal.
- F. None of above. chosen
Provenance (4 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_69f76e51d358819092bbc5f119f49476 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c82f8c88190bd77a086023ac0e1 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:10 p.m.