Triple
T36520484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MUH |
E900165
|
entity |
| Predicate | refersToCityServed |
P3936
|
FINISHED |
| Object | Mersa Matruh |
—
|
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: Mersa Matruh | Statement: [MUH, refersToCityServed, Mersa Matruh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refersToCityServed Context triple: [MUH, refersToCityServed, Mersa Matruh]
-
A.
associatedCityServed
Indicates that there is a relationship where a service, facility, or entity is linked to and serves a particular city.
-
B.
belongsToCityServedBy
Indicates that something is associated with or part of the city that is served by a particular service, facility, or infrastructure.
-
C.
alternativeCityServed
Indicates that one city functions as an alternative service location for another city, typically in contexts like transportation or logistics.
-
D.
servedCity
chosen
Indicates that a service, route, or facility operates in, reaches, or is available to a particular city.
-
E.
townServed
Indicates that a given service, facility, or infrastructure serves or provides coverage to a particular town.
- 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_69f76e5eedb88190a393b8c623f71dd7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
Created at: May 3, 2026, 4:11 p.m.