Triple
T28922846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LexCorp Tower |
E733564
|
entity |
| Predicate | inUniverseCityDistrict |
P143741
|
FINISHED |
| Object | downtown Metropolis |
—
|
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: downtown Metropolis | Statement: [LexCorp Tower, inUniverseCityDistrict, downtown Metropolis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inUniverseCityDistrict Context triple: [LexCorp Tower, inUniverseCityDistrict, downtown Metropolis]
-
A.
inCityDistrict
chosen
Indicates that one entity is located within the boundaries of a specific city district.
-
B.
targetCityDistrict
Indicates that one entity is a specific city district that serves as the target or destination in relation to another entity.
-
C.
cityOrDistrict
Indicates that the subject is classified as either a city or a district in relation to the object.
-
D.
cityDistrictLevel
Indicates that one administrative unit is a district-level subdivision within a given city in the territorial hierarchy.
-
E.
basedInDistrict
Indicates that an entity is located or has its primary base of operations within a specific administrative district.
- 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_69f05b0a5cc0819094828367ae204b70 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f67f7efc3c8190986d2d95b7a23729 |
completed | May 2, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69f67e40af9881908de3a4aa15f70a83 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 28, 2026, 8:21 a.m.