Triple
T5910529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Bridge Tower |
E131445
|
entity |
| Predicate | mainContractor |
P7138
|
FINISHED |
| Object | Mace |
E128288
|
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: Mace | Statement: [London Bridge Tower, mainContractor, Mace]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mace Context triple: [London Bridge Tower, mainContractor, Mace]
-
A.
Mace
chosen
Mace is a global construction and consultancy company known for delivering major high-profile projects, including landmark skyscrapers and complex infrastructure.
-
B.
Mace and Chain
Mace and Chain is an elite senior secret society at Yale University known for its selective membership and longstanding campus traditions.
-
C.
Cleave
Cleave is a given name variant of Clive, used as an alternative personal name or spelling.
-
D.
Weapemeoc
The Weapemeoc were an Algonquian-speaking Indigenous people who historically lived along the coastal regions of what is now northeastern North Carolina.
-
E.
The Hammer
The Hammer is the nickname of mixed martial artist and former UFC champion Matt Hamilton, known for his powerful striking style.
- 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_69c008593a44819081a07ae0efe6c574 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c037767af08190b5678cff9fd0816f |
completed | March 22, 2026, 6:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0b17375488190a3053d37712501b3 |
completed | March 23, 2026, 3:20 a.m. |
Created at: March 22, 2026, 3:59 p.m.