Triple
T9172123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kollam |
E220104
|
entity |
| Predicate | tradeHistory |
P58558
|
FINISHED |
| Object | traded with Romans |
—
|
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: traded with Romans | Statement: [Kollam, tradeHistory, traded with Romans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tradeHistory Context triple: [Kollam, tradeHistory, traded with Romans]
-
A.
tradeItemsHistorically
chosen
Indicates that the entities have engaged in trading items with each other at some point in the past.
-
B.
promotionHistory
Indicates the sequence of past promotions or advancement events that have occurred for an entity over time.
-
C.
ownershipHistory
Indicates the sequence of past and present owners associated with an entity over time.
-
D.
operatorHistory
Indicates a record of past actions, states, or changes associated with a particular operator over time.
-
E.
venueHistory
Indicates a historical relationship where a venue has previously hosted, been associated with, or served as the location for an event or activity.
- 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_69ca83e467108190abcae6a33b3d4dad |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccbf9fe79c819082f335c2fdd1c7d3 |
completed | April 1, 2026, 6:48 a.m. |
| PD | Predicate disambiguation | batch_69cc660761d88190ab6134b43b376964 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:22 p.m.