Triple
T35118910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faceless Men |
E1014114
|
entity |
| Predicate | laterTemple |
P202129
|
FINISHED |
| Object | Braavos |
—
|
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: Braavos | Statement: [Faceless Men, laterTemple, Braavos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterTemple Context triple: [Faceless Men, laterTemple, Braavos]
-
A.
mainTemple
Indicates that one entity serves as the primary or central temple associated with another entity.
-
B.
templeState
Indicates that a temple is in a particular condition, status, or phase (such as operational, under construction, abandoned, or ceremonial).
-
C.
associatedTemple
Indicates a relationship where one entity is linked or connected to a particular temple, typically as its relevant or related religious site.
-
D.
templeExpandedBy
Indicates that a temple has been enlarged, extended, or otherwise physically expanded through the actions or initiative of a specified agent or entity.
-
E.
hasTempleOf
Indicates that a location or entity possesses, contains, or is the site of a temple dedicated to a particular deity, figure, or purpose.
- 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_69f76dd8b6948190aaa32b081816bd94 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a0056174c908190be99c91a70393e47 |
completed | May 10, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_6a00538e7e08819091ecd4316cd641a1 |
completed | May 10, 2026, 9:44 a.m. |
| PDg | Predicate description generation | batch_6a0056164adc8190854a043a518e567a |
completed | May 10, 2026, 9:55 a.m. |
Created at: May 3, 2026, 4:01 p.m.