Triple
T25954287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Obelisk of Theodosius |
E654052
|
entity |
| Predicate | originalPair |
P46528
|
FINISHED |
| Object | one of a pair of obelisks at Karnak |
—
|
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 of a pair of obelisks at Karnak | Statement: [Obelisk of Theodosius, originalPair, one of a pair of obelisks at Karnak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalPair Context triple: [Obelisk of Theodosius, originalPair, one of a pair of obelisks at Karnak]
-
A.
commonPair
Indicates that two entities commonly occur together or are frequently associated as a pair in some shared context.
-
B.
dualPair
Indicates that two entities form a dual pair, standing in a mathematically defined dual relationship where each is the dual counterpart of the other.
-
C.
pairedSingleWith
Indicates that one entity is matched or associated as a single counterpart with another single entity, typically forming an exclusive one-to-one pairing.
-
D.
isPairOf
chosen
Indicates that two entities are associated as a matched or corresponding pair within a defined context.
-
E.
originalSide
Indicates that an entity remains on or is associated with its initial or starting side in a given context or relationship.
- 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_69e7ab40ac788190a771bc499eb1ae5f |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f7b2f3a104819098ddd8909eaf596c |
completed | May 3, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
Created at: April 22, 2026, 8:44 a.m.