Triple
T4618215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colossus of Rhodes |
E100917
|
entity |
| Predicate | estimatedWeight |
P1575
|
FINISHED |
| Object | over 20 tons of bronze |
—
|
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: over 20 tons of bronze | Statement: [Colossus of Rhodes, estimatedWeight, over 20 tons of bronze]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedWeight Context triple: [Colossus of Rhodes, estimatedWeight, over 20 tons of bronze]
-
A.
approximateWeightInPounds
Indicates the estimated weight of an entity expressed in pounds, rather than an exact measured value.
-
B.
emptyWeight
Indicates the weight of an object or vehicle when it is empty, excluding any load, cargo, or passengers.
-
C.
billedWeight
Indicates the weight value used for billing or charging purposes in a transaction or shipment.
-
D.
weightLimitInPounds
Indicates the maximum allowable weight for something, expressed in pounds.
-
E.
weight
chosen
Indicates a relationship where a numerical value quantifies how heavy an entity is, often used to measure or compare mass or load.
- 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_69bd43cf363c819087fd5ab441b4a3f4 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd59e247448190ad92f194cb1127c5 |
completed | March 20, 2026, 2:29 p.m. |
| PD | Predicate disambiguation | batch_69bd522fd5c48190ad2bffc0a5bc9061 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:12 p.m.