Triple
T28308425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penang Free School |
E713929
|
entity |
| Predicate | currentAddress |
P170808
|
FINISHED |
| Object | Green Lane, George Town, Penang |
—
|
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: Green Lane, George Town, Penang | Statement: [Penang Free School, currentAddress, Green Lane, George Town, Penang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentAddress Context triple: [Penang Free School, currentAddress, Green Lane, George Town, Penang]
-
A.
streetAddressNow
chosen
Indicates that an entity’s current street address is the specified location.
-
B.
locationAddressed
Indicates that a communication, message, or action is specifically directed to or intended for a particular location or address.
-
C.
currentlyLocatedAt
Indicates that an entity’s present or most recent known physical location is at the specified place.
-
D.
address
Indicates that one entity directs spoken or written communication specifically to another entity.
-
E.
streetAddress
Indicates the specific location of an entity in terms of its numbered building and street name within a postal address.
- 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_69efb5256afc8190b9322d25c3ae6320 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fcf825ca7081909d06b0df33eb33f9 |
completed | May 7, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fcf42160f0819096812a8bf590875e |
completed | May 7, 2026, 8:20 p.m. |
Created at: April 27, 2026, 11:39 p.m.