Triple
T35118909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faceless Men |
E1014114
|
entity |
| Predicate | firstTemple |
P101920
|
FINISHED |
| Object | Valyria |
E1025485
|
NE 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: Valyria | Statement: [Faceless Men, firstTemple, Valyria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstTemple Context triple: [Faceless Men, firstTemple, Valyria]
-
A.
firstTempleIn
chosen
Indicates that an entity is the earliest or original temple located in a specified place or region.
-
B.
firstTempleDestroyedBy
Indicates that the specified agent or force is responsible for destroying the first temple associated with the given entity.
-
C.
firstRulerTempleName
Indicates the name of the temple associated with the first ruler of an entity or domain.
-
D.
firstTempleDestructionDate
Indicates the date on which the First Temple was destroyed.
-
E.
secondTempleDestroyedBy
Indicates that the Second Temple was destroyed by the specified agent or cause.
- F. None of above.
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_69f76dd8b6948190aaa32b081816bd94 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37d94bcb9481909a58e1964c7179ce |
completed | June 21, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_6a037a016960819093ed4990fb4d9d36 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:01 p.m.