Triple
T7280681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hippodrome of Constantinople |
E163136
|
entity |
| Predicate | heightOfImportance |
P65467
|
FINISHED |
| Object | Byzantine period |
—
|
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: Byzantine period | Statement: [Hippodrome of Constantinople, heightOfImportance, Byzantine period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heightOfImportance Context triple: [Hippodrome of Constantinople, heightOfImportance, Byzantine period]
-
A.
peakImportance
chosen
Indicates that something reaches or represents the highest level of importance within a given context or timeframe.
-
B.
heightReference
Indicates that one entity’s height is being measured, compared, or defined relative to another specified reference point or standard.
-
C.
heightAboveSurroundings
Indicates that an entity’s vertical position or elevation is higher than that of its immediate surrounding area.
-
D.
heightClass
Indicates the categorical height level or range to which an entity is assigned (e.g., short, medium, tall).
-
E.
heightAboveGround
Indicates the vertical distance of an entity measured from the ground surface directly beneath it.
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb34fe0c8190a642fd3339f0cacd |
completed | March 27, 2026, 8:40 p.m. |
| PD | Predicate disambiguation | batch_69c6e76c5fbc8190b378830082f11cb0 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:59 p.m.