Triple
T28889950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tower of Guard |
E732667
|
entity |
| Predicate | formerNameOfRelatedCity |
P196280
|
FINISHED |
| Object | Minas Anor |
—
|
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: Minas Anor | Statement: [Tower of Guard, formerNameOfRelatedCity, Minas Anor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerNameOfRelatedCity Context triple: [Tower of Guard, formerNameOfRelatedCity, Minas Anor]
-
A.
formerCityName
Indicates that an entity was previously known by a different city name in the past.
-
B.
hasAssociatedCityFormerName
Indicates that an entity is linked to a city by referencing one of that city's former or historical names.
-
C.
formerNameOfCapital
Indicates that one entity was the previous official name of a capital city before it was renamed.
-
D.
refersToFormerNameOfComparisonCity
Indicates that the subject entity refers to a previous or former name of the comparison city.
-
E.
formerNameOfCityServed
Indicates that one name was previously used for a city that is (or was) served by a particular entity, before being replaced by its current name.
- 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_69f05b07bdec819080cadfe147aa1f25 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69fe1fd637c08190aa95cd2478c278cb |
completed | May 8, 2026, 5:39 p.m. |
| PD | Predicate disambiguation | batch_69fe19344bb481909b5e2144155e4add |
completed | May 8, 2026, 5:11 p.m. |
| PDg | Predicate description generation | batch_69fe1fd58ad8819093d3d705e8521014 |
completed | May 8, 2026, 5:39 p.m. |
Created at: April 28, 2026, 7:54 a.m.