Triple
T34827783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philomelium |
E1003977
|
entity |
| Predicate | hasApproximateModernLocation |
P54388
|
FINISHED |
| Object | near Akşehir |
—
|
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: near Akşehir | Statement: [Philomelium, hasApproximateModernLocation, near Akşehir]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateModernLocation Context triple: [Philomelium, hasApproximateModernLocation, near Akşehir]
-
A.
locatedInOrNearModernSettlement
chosen
Indicates that something is situated within or in close proximity to a present-day town, city, or other populated settlement.
-
B.
hasModernLocation
Indicates that an entity is currently situated in, or corresponds to, a specified modern geographic or administrative location.
-
C.
uncertainModernLocation
Indicates that the present-day geographic location associated with an entity is not known with certainty or cannot be reliably determined.
-
D.
historicallyLocatedNear
Indicates that, in a historical context, one entity was geographically situated close to another entity.
-
E.
historicalLocationOf
Indicates that a place served as a significant site or setting for an entity during a particular historical period or event.
- 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_69f76db7d1b4819093bd4912d80d845d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd9ff026a48190bfec33deeb3b2c43 |
completed | May 8, 2026, 8:33 a.m. |
| PD | Predicate disambiguation | batch_69fd97d805bc8190ba12f429d3ad04c7 |
completed | May 8, 2026, 7:59 a.m. |
Created at: May 3, 2026, 4 p.m.