Triple
T12586705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maze Hill |
E300481
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object | MZH |
E854015
|
NE 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: MZH | Statement: [Maze Hill, hasStationCode, MZH]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MZH Context triple: [Maze Hill, hasStationCode, MZH]
-
A.
MZH
chosen
MZH is the National Rail station code for Maze Hill railway station in southeast London.
-
B.
ZMH
ZMH is the three-letter station code used to identify Mansion House Underground station on the London Underground network.
-
C.
ZMH
ZMH is the former stock ticker symbol for Zimmer Holdings, a major medical device company specializing in orthopedic products such as joint replacement implants.
-
D.
Zizhan
Zizhan is the courtesy name of Su Shi, the renowned Song dynasty Chinese poet, calligrapher, and statesman also known as Su Dongpo.
-
E.
Muzong
Muzong is the temple name of the Longqing Emperor, a Ming dynasty ruler of China who reigned from 1567 to 1572.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bde87b648190bcd0266e9efde098 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954bbe72c8190aa11090bb6b480c9 |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ebed164819083fbdaa775a59cd4 |
completed | May 2, 2026, 8:29 p.m. |
Created at: April 9, 2026, 5:05 p.m.