Triple
T5222687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yeoman Warders |
E117907
|
entity |
| Predicate | tourFormat |
P62123
|
FINISHED |
| Object | guided walking tours of the Tower of London grounds |
—
|
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: guided walking tours of the Tower of London grounds | Statement: [Yeoman Warders, tourFormat, guided walking tours of the Tower of London grounds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tourFormat Context triple: [Yeoman Warders, tourFormat, guided walking tours of the Tower of London grounds]
-
A.
competitionFormat
Indicates the specific structure or ruleset under which a competition is organized and conducted.
-
B.
trialFormat
Indicates the specific structure, rules, or procedural setup under which a trial or experimental process is conducted.
-
C.
tourStatus
Indicates the current state or phase of a tour within its overall lifecycle (e.g., planned, active, completed, or canceled).
-
D.
worldCupFormat
Indicates the specific structure, rules, and progression system used to organize and play a given World Cup competition.
-
E.
tourLevel
Indicates the relative difficulty, expertise, or experience level associated with a particular tour or guided activity.
- F. None of above. chosen
Provenance (4 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_69bd4465e03081909bfcfd7113062590 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7abba82881908c030ba55146b8ea |
completed | March 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69bd77bd2a448190a9ae5afd2585a7b9 |
completed | March 20, 2026, 4:37 p.m. |
| PDg | Predicate description generation | batch_69bd78a89b608190b259d3d8658f8f7c |
completed | March 20, 2026, 4:41 p.m. |
Created at: March 20, 2026, 1:48 p.m.