Triple
T4102575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jaffa Gate |
E87973
|
entity |
| Predicate | sideOfOldCity |
P31586
|
FINISHED |
| Object | western side |
—
|
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: western side | Statement: [Jaffa Gate, sideOfOldCity, western side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sideOfOldCity Context triple: [Jaffa Gate, sideOfOldCity, western side]
-
A.
locatedInOldCity
Indicates that an entity is situated within the boundaries of an old or historic part of a city.
-
B.
Warsaw Old Town
Indicates the relationship of being located in or associated with the historic central district known as Warsaw Old Town.
-
C.
hasCitySide
chosen
Indicates that one entity is located on or corresponds to a particular side or area of a city relative to another entity.
-
D.
ancientCity
Indicates that the subject is a historically old or long-established city, typically originating from ancient times.
-
E.
oneOfOldestCities
Indicates that the subject is among the oldest cities within a specified group, region, or 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_69aed94564cc8190a9c1457daedb6e7f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd1012208190ab0980c661d6bc41 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90b2ef08190ae84febfd69dd48b |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:40 p.m.