Triple
T38589304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Spire |
E932416
|
entity |
| Predicate | finalApproachTo |
P199948
|
FINISHED |
| Object | Frozen Throne |
—
|
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: Frozen Throne | Statement: [The Spire, finalApproachTo, Frozen Throne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalApproachTo Context triple: [The Spire, finalApproachTo, Frozen Throne]
-
A.
usedToApproach
Indicates that one entity employed another entity as a means or method to move closer to or reach a target entity or location.
-
B.
hasInstrumentApproach
Indicates that an approach procedure to a location or runway is conducted using specified navigation instruments or instrument-based methods.
-
C.
approachControl
Indicates that one entity moves closer to another entity in a deliberate or controlled manner.
-
D.
finalAttitude
Indicates the ultimate stance, feeling, or evaluative judgment one entity holds toward another entity or situation after a process or interaction has concluded.
-
E.
visualApproach
Indicates that one entity moves toward or aligns with another primarily using visual cues or sight-based guidance.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff64b957bc81908afbc5914234a8ea |
completed | May 9, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69ff6446593c81909173e296eea2590c |
completed | May 9, 2026, 4:43 p.m. |
| PDg | Predicate description generation | batch_69ff64b864f481909fcefc2b08595c89 |
completed | May 9, 2026, 4:45 p.m. |
Created at: May 3, 2026, 4:32 p.m.