Triple
T14780178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shae |
E347369
|
entity |
| Predicate | firstMet |
P58222
|
FINISHED |
| Object | Tyrion Lannister at the Green Fork during the War of the Five Kings |
—
|
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: Tyrion Lannister at the Green Fork during the War of the Five Kings | Statement: [Shae, firstMet, Tyrion Lannister at the Green Fork during the War of the Five Kings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstMet Context triple: [Shae, firstMet, Tyrion Lannister at the Green Fork during the War of the Five Kings]
-
A.
firstMeets
chosen
Indicates that one entity encounters or comes into contact with another entity for the first time.
-
B.
first
Indicates that one entity precedes all others in an ordered sequence or ranking.
-
C.
firstOrdinary
Indicates that the subject is the first entity to hold or occupy an ordinary (non-special, standard) position, role, or status in a given sequence or context.
-
D.
firstToFeature
Indicates that one entity was the earliest or initial subject to exhibit, include, or present another entity in a given context.
-
E.
firstEncounteredBy
Indicates that one entity is the person or agent who initially discovered, met, or came across the other entity for the first time.
- 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_69d822e9b9e08190bedcc31a163fda82 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deca9c7cac8190ba900df95e42e318 |
completed | April 14, 2026, 11:15 p.m. |
| PD | Predicate disambiguation | batch_69de8c090d1081909b5a9bf437499d6c |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:31 a.m.