Triple
T1563255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basilica Cistern |
E33374
|
entity |
| Predicate | MedusaHeadOrientation |
P1101
|
FINISHED |
| Object | one upside down |
—
|
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: one upside down | Statement: [Basilica Cistern, MedusaHeadOrientation, one upside down]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MedusaHeadOrientation Context triple: [Basilica Cistern, MedusaHeadOrientation, one upside down]
-
A.
shaftOrientation
Indicates the directional alignment or angle at which a shaft is positioned or oriented relative to a reference frame or object.
-
B.
legOrientation
Indicates the relative positioning or directional alignment of an entity’s leg(s) with respect to a reference frame or another object.
-
C.
orientation
chosen
Indicates the relative directional alignment or facing of one entity with respect to another or to a reference frame.
-
D.
gateOrientation
Indicates the directional alignment or facing direction of a gate relative to a reference frame or coordinate system.
-
E.
sessionOrientation
Indicates the directional or spatial alignment relationship established between entities within a session or interaction context.
- 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_69a885ef9cf48190b0af0f5ce3d02231 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90fccd4b48190a44012888a00af7f |
completed | March 5, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69a907b872f0819096b3df6ad502c63e |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:27 p.m.