Triple
T36103302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aegon V Targaryen |
E1044280
|
entity |
| Predicate | swornSwordAndCompanion |
P115487
|
FINISHED |
| Object | Ser Duncan the Tall |
—
|
NE NERFINISHED |
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: Ser Duncan the Tall | Statement: [Aegon V Targaryen, swornSwordAndCompanion, Ser Duncan the Tall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: swornSwordAndCompanion Context triple: [Aegon V Targaryen, swornSwordAndCompanion, Ser Duncan the Tall]
-
A.
swornSword
chosen
Indicates a formal oath of loyalty in which one entity pledges to serve and protect another as their sworn sword.
-
B.
swornBrother
Indicates a relationship where two or more individuals have formally pledged brotherhood to each other, typically through an oath signifying deep loyalty and mutual support.
-
C.
swordsFeature
Indicates that something includes or prominently presents swords as a notable element or characteristic.
-
D.
tinctureOfSword
Indicates that something is a medicinal or alchemical tincture prepared from, associated with, or derived from a sword.
-
E.
swordsman
Indicates that an entity is a person who practices or is skilled in the use of swords.
- 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_69f76e338e2c8190b7f3bc68bec76349 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b3e2f3c08190be4fd1ae4fa1266d |
completed | May 3, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bcc47081909fe7d592ac69006c |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.