Triple
T4294123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Outremer |
E99666
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Acre |
E57659
|
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: Acre | Statement: [Outremer, capital, Acre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Acre Context triple: [Outremer, capital, Acre]
-
A.
Acre
chosen
Acre is an ancient port city on the Mediterranean coast of present-day Israel, renowned for its well-preserved Crusader and Ottoman architecture and its long, strategic history.
-
B.
Luas
Luas is Dublin’s modern light rail tram system, providing frequent urban and suburban public transport across the city and its surrounding areas.
-
C.
Amapro
Amapro is a Japanese production company known for its involvement in creating television and film projects such as the crime drama series "Tokyo Vice."
-
D.
أوقية
أوقية هي وحدة العملة الرسمية في موريتانيا وتُستخدم في التعاملات المالية اليومية في البلاد.
-
E.
Patria Land
Patria Land is a defense industry company specializing in the design and manufacture of armored vehicles and land-based military systems.
- 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_69b3455175088190aa79c6e03b86647e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35083f87c8190a3d3b323e76ab575 |
completed | March 12, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5c73d47448190a844bc13eae84a54 |
completed | March 14, 2026, 8:38 p.m. |
Created at: March 12, 2026, 11:08 p.m.